Abstract is missing.
- Interactive Weak Supervision: Learning Useful Heuristics for Data LabelingBenedikt Boecking, Willie Neiswanger, Eric P. Xing, Artur Dubrawski. [doi]
- Learnable Embedding sizes for Recommender SystemsSiyi Liu, Chen Gao, Yihong Chen, Depeng Jin, Yong Li 0008. [doi]
- Robust Learning of Fixed-Structure Bayesian Networks in Nearly-Linear TimeYu Cheng, Honghao Lin. [doi]
- Efficient Reinforcement Learning in Factored MDPs with Application to Constrained RLXiaoyu Chen, Jiachen Hu, Lihong Li, Liwei Wang 0001. [doi]
- Revisiting Hierarchical Approach for Persistent Long-Term Video PredictionWonkwang Lee, Whie Jung, Han Zhang, Ting Chen, Jing Yu Koh, Thomas E. Huang, Hyungsuk Yoon, Honglak Lee, Seunghoon Hong. [doi]
- DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation DialoguesRishabh Joshi, Vidhisha Balachandran, Shikhar Vashishth, Alan W. Black, Yulia Tsvetkov. [doi]
- Learning the Pareto Front with HypernetworksAviv Navon, Aviv Shamsian, Ethan Fetaya, Gal Chechik. [doi]
- Perceptual Adversarial Robustness: Defense Against Unseen Threat ModelsCassidy Laidlaw, Sahil Singla 0002, Soheil Feizi. [doi]
- Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning RateJingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu. [doi]
- Augmenting Physical Models with Deep Networks for Complex Dynamics ForecastingYuan Yin, Vincent Le Guen, Jérémie Donà, Emmanuel de Bézenac, Ibrahim Ayed, Nicolas Thome, Patrick Gallinari. [doi]
- Unsupervised Object Keypoint Learning using Local Spatial PredictabilityAnand Gopalakrishnan, Sjoerd van Steenkiste, Jürgen Schmidhuber. [doi]
- Learning advanced mathematical computations from examplesFrançois Charton, Amaury Hayat, Guillaume Lample. [doi]
- AdaSpeech: Adaptive Text to Speech for Custom VoiceMingjian Chen, Xu Tan 0003, Bohan Li, Yanqing Liu, Tao Qin, Sheng Zhao, Tie-Yan Liu. [doi]
- Learning to Generate 3D Shapes with Generative Cellular AutomataDongsu Zhang, Changwoon Choi, Jeonghwan Kim, Young-Min Kim. [doi]
- Understanding and Improving Lexical Choice in Non-Autoregressive TranslationLiang Ding, Longyue Wang, Xuebo Liu 0002, Derek F. Wong, Dacheng Tao, Zhaopeng Tu. [doi]
- Conformation-Guided Molecular Representation with Hamiltonian Neural NetworksZiyao Li, Shuwen Yang, Guojie Song, Lingsheng Cai. [doi]
- Neural Topic Model via Optimal TransportHe Zhao, Dinh Phung, Viet Huynh, Trung Le, Wray L. Buntine. [doi]
- Learning perturbation sets for robust machine learningEric Wong 0001, J. Zico Kolter. [doi]
- Generative Scene Graph NetworksFei Deng, Zhuo Zhi, Donghun Lee, Sungjin Ahn. [doi]
- Learning Task Decomposition with Ordered Memory Policy NetworkYuchen Lu, Yikang Shen, Siyuan Zhou, Aaron Courville, Joshua B. Tenenbaum, Chuang Gan. [doi]
- Hierarchical Autoregressive Modeling for Neural Video CompressionRuihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt. [doi]
- Learning to Sample with Local and Global Contexts in Experience Replay BufferYoungmin Oh, Kimin Lee, Jinwoo Shin, Eunho Yang, Sung Ju Hwang. [doi]
- Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine TranslationJungo Kasai, Nikolaos Pappas 0002, Hao Peng, James Cross, Noah A. Smith. [doi]
- Reweighting Augmented Samples by Minimizing the Maximal Expected LossMingyang Yi, Lu Hou, Lifeng Shang, Xin Jiang, Qun Liu, Zhi-Ming Ma. [doi]
- Geometry-Aware Gradient Algorithms for Neural Architecture SearchLiam Li, Mikhail Khodak, Nina Balcan, Ameet Talwalkar. [doi]
- Language-Agnostic Representation Learning of Source Code from Structure and ContextDaniel Zügner, Tobias Kirschstein, Michele Catasta, Jure Leskovec, Stephan Günnemann. [doi]
- Disambiguating Symbolic Expressions in Informal DocumentsDennis Müller 0001, Cezary Kaliszyk. [doi]
- Revisiting Dynamic Convolution via Matrix DecompositionYunsheng Li, Yinpeng Chen, Xiyang Dai, Mengchen Liu, Dongdong Chen, Ye Yu, Lu Yuan, Zicheng Liu 0001, Mei Chen, Nuno Vasconcelos. [doi]
- Implicit Gradient RegularizationDavid G. T. Barrett, Benoit Dherin. [doi]
- Differentiable Segmentation of SequencesErik Scharwächter, Jonathan Lennartz, Emmanuel Müller. [doi]
- Learning Incompressible Fluid Dynamics from Scratch - Towards Fast, Differentiable Fluid Models that GeneralizeNils Wandel, Michael Weinmann, Reinhard Klein. [doi]
- Isometric Propagation Network for Generalized Zero-shot LearningLu Liu, Tianyi Zhou, Guodong Long, Jing Jiang, Xuanyi Dong, Chengqi Zhang. [doi]
- Neural Synthesis of Binaural Speech From Mono AudioAlexander Richard, Dejan Markovic, Israel D. Gebru, Steven Krenn, Gladstone Alexander Butler, Fernando De la Torre, Yaser Sheikh. [doi]
- The Recurrent Neural Tangent KernelSina Alemohammad, Zichao Wang 0001, Randall Balestriero, Richard G. Baraniuk. [doi]
- Quantifying Differences in Reward FunctionsAdam Gleave, Michael Dennis 0001, Shane Legg, Stuart Russell, Jan Leike. [doi]
- Adaptive Extra-Gradient Methods for Min-Max Optimization and GamesKimon Antonakopoulos, Elena Veronica Belmega, Panayotis Mertikopoulos. [doi]
- Decoupling Global and Local Representations via Invertible Generative FlowsXuezhe Ma, Xiang Kong, Shanghang Zhang, Eduard H. Hovy. [doi]
- Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual ModelsZirui Wang, Yulia Tsvetkov, Orhan Firat, Yuan Cao 0007. [doi]
- Gradient Projection Memory for Continual LearningGobinda Saha, Isha Garg, Kaushik Roy 0001. [doi]
- Learning Cross-Domain Correspondence for Control with Dynamics Cycle-ConsistencyQiang Zhang, Tete Xiao, Alexei A. Efros, Lerrel Pinto, Xiaolong Wang. [doi]
- Distributional Sliced-Wasserstein and Applications to Generative ModelingKhai Nguyen, Nhat Ho, Tung Pham, Hung Bui. [doi]
- Model-Based Visual Planning with Self-Supervised Functional DistancesStephen Tian, Suraj Nair, Frederik Ebert, Sudeep Dasari, Benjamin Eysenbach, Chelsea Finn, Sergey Levine. [doi]
- Mutual Information State Intrinsic ControlRui Zhao, Yang Gao, Pieter Abbeel, Volker Tresp, Wei Xu. [doi]
- Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement LearningAviral Kumar, Rishabh Agarwal, Dibya Ghosh, Sergey Levine. [doi]
- Randomized Automatic DifferentiationDeniz Oktay, Nick McGreivy, Joshua Aduol, Alex Beatson, Ryan P. Adams. [doi]
- Bag of Tricks for Adversarial TrainingTianyu Pang, Xiao Yang, Yinpeng Dong, Hang Su, Jun Zhu. [doi]
- On InstaHide, Phase Retrieval, and Sparse Matrix FactorizationSitan Chen, Xiaoxiao Li, Zhao Song 0002, Danyang Zhuo. [doi]
- Robust and Generalizable Visual Representation Learning via Random ConvolutionsZhenlin Xu, Deyi Liu, Junlin Yang, Colin Raffel, Marc Niethammer. [doi]
- What Makes Instance Discrimination Good for Transfer Learning?Nanxuan Zhao, Zhirong Wu, Rynson W. H. Lau, Stephen Lin. [doi]
- DINO: A Conditional Energy-Based GAN for Domain TranslationKonstantinos Vougioukas, Stavros Petridis, Maja Pantic. [doi]
- Active Contrastive Learning of Audio-Visual Video RepresentationsShuang Ma, Zhaoyang Zeng, Daniel J. McDuff, Yale Song. [doi]
- Are wider nets better given the same number of parameters?Anna Golubeva, Guy Gur-Ari, Behnam Neyshabur. [doi]
- Contrastive Learning with Adversarial Perturbations for Conditional Text GenerationSeanie Lee, Dong-Bok Lee, Sung Ju Hwang. [doi]
- Lipschitz Recurrent Neural NetworksN. Benjamin Erichson, Omri Azencot, Alejandro Queiruga, Liam Hodgkinson, Michael W. Mahoney. [doi]
- Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated LearningHaibo Yang, Minghong Fang, Jia Liu. [doi]
- Explaining by Imitating: Understanding Decisions by Interpretable Policy LearningAlihan Hüyük, Daniel Jarrett, Cem Tekin, Mihaela van der Schaar. [doi]
- Tent: Fully Test-Time Adaptation by Entropy MinimizationDequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno A. Olshausen, Trevor Darrell. [doi]
- Optimal Regularization can Mitigate Double DescentPreetum Nakkiran, Prayaag Venkat, Sham M. Kakade, Tengyu Ma. [doi]
- Bayesian Few-Shot Classification with One-vs-Each Pólya-Gamma Augmented Gaussian ProcessesJake Snell, Richard S. Zemel. [doi]
- Proximal Gradient Descent-Ascent: Variable Convergence under KŁ GeometryZiyi Chen 0002, Yi Zhou, Tengyu Xu, Yingbin Liang. [doi]
- A Geometric Analysis of Deep Generative Image Models and Its ApplicationsBinxu Wang, Carlos R. Ponce. [doi]
- Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space NavigationPeiye Zhuang, Oluwasanmi Koyejo, Alexander G. Schwing. [doi]
- Neural Learning of One-of-Many Solutions for Combinatorial Problems in Structured Output SpacesYatin Nandwani, Deepanshu Jindal, Mausam, Parag Singla. [doi]
- Blending MPC & Value Function Approximation for Efficient Reinforcement LearningMohak Bhardwaj, Sanjiban Choudhury, Byron Boots. [doi]
- A statistical theory of cold posteriors in deep neural networksLaurence Aitchison. [doi]
- Towards Impartial Multi-task LearningLiyang Liu, Yi Li, Zhanghui Kuang, Jing-Hao Xue, Yimin Chen, Wenming Yang, Qingmin Liao, Wayne Zhang. [doi]
- C-Learning: Learning to Achieve Goals via Recursive ClassificationBenjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine. [doi]
- Plan-Based Relaxed Reward Shaping for Goal-Directed TasksIngmar Schubert, Ozgur S. Oguz, Marc Toussaint. [doi]
- Federated Learning Based on Dynamic RegularizationDurmus Alp Emre Acar, Yue Zhao, Ramon Matas Navarro, Matthew Mattina, Paul N. Whatmough, Venkatesh Saligrama. [doi]
- Differentially Private Learning Needs Better Features (or Much More Data)Florian Tramèr, Dan Boneh. [doi]
- Distilling Knowledge from Reader to Retriever for Question AnsweringGautier Izacard, Edouard Grave. [doi]
- Deep Learning meets Projective ClusteringAlaa Maalouf, Harry Lang, Daniela Rus, Dan Feldman. [doi]
- Contrastive Explanations for Reinforcement Learning via Embedded Self PredictionsZhengxian Lin, Kin-Ho Lam, Alan Fern. [doi]
- Getting a CLUE: A Method for Explaining Uncertainty EstimatesJavier Antorán, Umang Bhatt, Tameem Adel, Adrian Weller, José Miguel Hernández-Lobato. [doi]
- Knowledge distillation via softmax regression representation learningJing Yang 0038, Brais Martínez, Adrian Bulat, Georgios Tzimiropoulos. [doi]
- Nonseparable Symplectic Neural NetworksShiying Xiong, Yunjin Tong, Xingzhe He, Shuqi Yang, Cheng Yang, Bo Zhu 0002. [doi]
- AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant WeightsByeongho Heo, Sanghyuk Chun, Seong Joon Oh, Dongyoon Han, Sangdoo Yun, Gyuwan Kim, Youngjung Uh, Jung-Woo Ha 0001. [doi]
- Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor ProjectionsCsaba Tóth, Patric Bonnier, Harald Oberhauser. [doi]
- Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech SynthesisRafael Valle, Kevin J. Shih, Ryan Prenger, Bryan Catanzaro. [doi]
- Gradient Descent on Neural Networks Typically Occurs at the Edge of StabilityJeremy M. Cohen, Simran Kaur, Yuanzhi Li, J. Zico Kolter, Ameet Talwalkar. [doi]
- BRECQ: Pushing the Limit of Post-Training Quantization by Block ReconstructionYuhang Li, Ruihao Gong, Xu Tan, Yang Yang, Peng Hu, Qi Zhang, Fengwei Yu, Wei Wang, Shi Gu. [doi]
- How to Find Your Friendly Neighborhood: Graph Attention Design with Self-SupervisionDongkwan Kim, Alice H. Oh. [doi]
- Explaining the Efficacy of Counterfactually Augmented DataDivyansh Kaushik, Amrith Setlur, Eduard H. Hovy, Zachary Chase Lipton. [doi]
- Mirostat: a Neural Text decoding Algorithm that directly controls perplexitySourya Basu, Govardana Sachitanandam Ramachandran, Nitish Shirish Keskar, Lav R. Varshney. [doi]
- RMSprop converges with proper hyper-parameterNaichen Shi, Dawei Li, Mingyi Hong, Ruoyu Sun 0001. [doi]
- Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural RenderingYuxuan Zhang, Wenzheng Chen, Huan Ling, Jun Gao, Yinan Zhang, Antonio Torralba 0001, Sanja Fidler. [doi]
- Learning Robust State Abstractions for Hidden-Parameter Block MDPsAmy Zhang 0001, Shagun Sodhani, Khimya Khetarpal, Joelle Pineau. [doi]
- Uncertainty Estimation in Autoregressive Structured PredictionAndrey Malinin, Mark J. F. Gales. [doi]
- Scaling the Convex Barrier with Active SetsAlessandro De Palma, Harkirat S. Behl, Rudy R. Bunel, Philip H. S. Torr, M. Pawan Kumar. [doi]
- Deberta: decoding-Enhanced Bert with Disentangled AttentionPengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu Chen. [doi]
- CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer LearningOssama Ahmed, Frederik Träuble, Anirudh Goyal, Alexander Neitz, Manuel Wuthrich, Yoshua Bengio, Bernhard Schölkopf, Stefan Bauer. [doi]
- Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov WassersteinKhai Nguyen, Son Nguyen, Nhat Ho, Tung Pham, Hung Bui. [doi]
- Practical Real Time Recurrent Learning with a Sparse ApproximationJacob Menick, Erich Elsen, Utku Evci, Simon Osindero, Karen Simonyan, Alex Graves. [doi]
- Growing Efficient Deep Networks by Structured Continuous SparsificationXin Yuan, Pedro Henrique Pamplona Savarese, Michael Maire. [doi]
- DynaTune: Dynamic Tensor Program Optimization in Deep Neural Network CompilationMinjia Zhang, Menghao Li, Chi Wang, Mingqin Li. [doi]
- Projected Latent Markov Chain Monte Carlo: Conditional Sampling of Normalizing FlowsChris Cannella, Mohammadreza Soltani, Vahid Tarokh. [doi]
- In Search of Lost Domain GeneralizationIshaan Gulrajani, David Lopez-Paz. [doi]
- WaNet - Imperceptible Warping-based Backdoor AttackTuan-Anh Nguyen, Anh-Tuan Tran. [doi]
- More or Less: When and How to Build Convolutional Neural Network EnsemblesAbdul Wasay, Stratos Idreos. [doi]
- Mathematical Reasoning via Self-supervised Skip-tree TrainingMarkus Norman Rabe, Dennis Lee 0003, Kshitij Bansal, Christian Szegedy. [doi]
- On the Universality of Rotation Equivariant Point Cloud NetworksNadav Dym, Haggai Maron. [doi]
- Unbiased Teacher for Semi-Supervised Object DetectionYen-Cheng Liu, Chih-Yao Ma, Zijian He, Chia-Wen Kuo, Kan Chen, Peizhao Zhang, Bichen Wu, Zsolt Kira, Peter Vajda. [doi]
- Rapid Neural Architecture Search by Learning to Generate Graphs from DatasetsHayeon Lee, Eunyoung Hyung, Sung Ju Hwang. [doi]
- Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement LearningValerie Chen, Abhinav Gupta 0001, Kenneth Marino. [doi]
- Robust Pruning at InitializationSoufiane Hayou, Jean-Francois Ton, Arnaud Doucet, Yee Whye Teh. [doi]
- Unsupervised Audiovisual Synthesis via Exemplar AutoencodersKangle Deng, Aayush Bansal, Deva Ramanan. [doi]
- Bidirectional Variational Inference for Non-Autoregressive Text-to-SpeechYoonhyung Lee, Joongbo Shin, Kyomin Jung. [doi]
- Fair Mixup: Fairness via InterpolationChing-Yao Chuang, Youssef Mroueh. [doi]
- Monte-Carlo Planning and Learning with Language Action Value EstimatesYoungsoo Jang, Seokin Seo, Jongmin Lee 0004, Kee-Eung Kim. [doi]
- Learning explanations that are hard to varyGiambattista Parascandolo, Alexander Neitz, Antonio Orvieto, Luigi Gresele, Bernhard Schölkopf. [doi]
- Inductive Representation Learning in Temporal Networks via Causal Anonymous WalksYanbang Wang, Yen-Yu Chang, Yunyu Liu, Jure Leskovec, Pan Li 0005. [doi]
- Empirical Analysis of Unlabeled Entity Problem in Named Entity RecognitionYangming Li, Lemao Liu, Shuming Shi 0001. [doi]
- SenSeI: Sensitive Set Invariance for Enforcing Individual FairnessMikhail Yurochkin, Yuekai Sun. [doi]
- MiCE: Mixture of Contrastive Experts for Unsupervised Image ClusteringTsung Wei Tsai, Chongxuan Li, Jun Zhu. [doi]
- Multiscale Score Matching for Out-of-Distribution DetectionAhsan Mahmood, Junier Oliva, Martin Andreas Styner. [doi]
- Graph Edit NetworksBenjamin Paassen, Daniele Grattarola, Daniele Zambon, Cesare Alippi, Barbara Hammer. [doi]
- Why resampling outperforms reweighting for correcting sampling bias with stochastic gradientsJing An, Lexing Ying, Yuhua Zhu. [doi]
- A Critique of Self-Expressive Deep Subspace ClusteringBenjamin David Haeffele, Chong You, René Vidal. [doi]
- Meta-Learning with Neural Tangent KernelsYufan Zhou, Zhenyi Wang, Jiayi Xian, Changyou Chen, Jinhui Xu 0001. [doi]
- Answering Complex Open-Domain Questions with Multi-Hop Dense RetrievalWenhan Xiong, Xiang Lorraine Li, Srini Iyer, Jingfei Du, Patrick S. H. Lewis, William Yang Wang, Yashar Mehdad, Scott Yih, Sebastian Riedel 0001, Douwe Kiela, Barlas Oguz. [doi]
- LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial RecognitionValeriia Cherepanova, Micah Goldblum, Harrison Foley, Shiyuan Duan, John P. Dickerson, Gavin Taylor, Tom Goldstein. [doi]
- SAFENet: A Secure, Accurate and Fast Neural Network InferenceQian Lou, Yilin Shen, Hongxia Jin, Lei Jiang 0001. [doi]
- Risk-Averse Offline Reinforcement LearningNúria Armengol Urpí, Sebastian Curi, Andreas Krause 0001. [doi]
- Efficient Empowerment Estimation for Unsupervised StabilizationRuihan Zhao 0001, Kevin Lu, Pieter Abbeel, Stas Tiomkin. [doi]
- IEPT: Instance-Level and Episode-Level Pretext Tasks for Few-Shot LearningManli Zhang, Jianhong Zhang, Zhiwu Lu, Tao Xiang, Mingyu Ding, Songfang Huang. [doi]
- Auxiliary Task Update Decomposition: the Good, the Bad and the neutralLucio M. Dery, Yann N. Dauphin, David Grangier. [doi]
- PDE-Driven Spatiotemporal DisentanglementJérémie Donà, Jean-Yves Franceschi, Sylvain Lamprier, Patrick Gallinari. [doi]
- Nearest Neighbor Machine TranslationUrvashi Khandelwal, Angela Fan, Dan Jurafsky, Luke Zettlemoyer, Mike Lewis. [doi]
- Unsupervised Meta-Learning through Latent-Space Interpolation in Generative ModelsSiavash Khodadadeh, Sharare Zehtabian, Saeed Vahidian, Weijia Wang, Bill Lin, Ladislau Böloöi. [doi]
- Refining Deep Generative Models via Discriminator Gradient FlowAbdul Fatir Ansari, Ming Liang Ang, Harold Soh. [doi]
- Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial TimeTolga Ergen, Mert Pilanci. [doi]
- Understanding Over-parameterization in Generative Adversarial NetworksYogesh Balaji, Mohammadmahdi Sajedi, Neha Mukund Kalibhat, Mucong Ding, Dominik Stöger, Mahdi Soltanolkotabi, Soheil Feizi. [doi]
- Dataset Condensation with Gradient MatchingBo Zhao, Konda Reddy Mopuri, Hakan Bilen. [doi]
- Locally Free Weight Sharing for Network Width SearchXiu Su, Shan You, Tao Huang, Fei Wang 0032, Chen Qian 0006, Changshui Zhang, Chang Xu 0002. [doi]
- IsarStep: a Benchmark for High-level Mathematical ReasoningWenda Li, Lei Yu, Yuhuai Wu, Lawrence C. Paulson. [doi]
- FedBE: Making Bayesian Model Ensemble Applicable to Federated LearningHong-You Chen, Wei-Lun Chao. [doi]
- DARTS-: Robustly Stepping out of Performance Collapse Without IndicatorsXiangxiang Chu, Xiaoxing Wang, Bo Zhang 0046, Shun Lu, Xiaolin Wei, Junchi Yan. [doi]
- Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural NetworksYige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu, Bo Li, Xingjun Ma. [doi]
- CcGAN: Continuous Conditional Generative Adversarial Networks for Image GenerationXin Ding, Yongwei Wang, Zuheng Xu, William J. Welch, Z. Jane Wang 0001. [doi]
- A PAC-Bayesian Approach to Generalization Bounds for Graph Neural NetworksRenjie Liao, Raquel Urtasun, Richard S. Zemel. [doi]
- Large Batch Simulation for Deep Reinforcement LearningBrennan Shacklett, Erik Wijmans, Aleksei Petrenko, Manolis Savva, Dhruv Batra, Vladlen Koltun, Kayvon Fatahalian. [doi]
- Shapley Explanation NetworksRui Wang, Xiaoqian Wang, David I. Inouye. [doi]
- Individually Fair Gradient BoostingAlexander Vargo, Fan Zhang, Mikhail Yurochkin, Yuekai Sun. [doi]
- RNNLogic: Learning Logic Rules for Reasoning on Knowledge GraphsMeng Qu, Junkun Chen, Louis-Pascal Xhonneux, Yoshua Bengio, Jian Tang. [doi]
- Learning to Make Decisions via Submodular RegularizationAyya Alieva, Aiden Aceves, Jialin Song, Stephen Mayo, Yisong Yue, Yuxin Chen 0001. [doi]
- SEDONA: Search for Decoupled Neural Networks toward Greedy Block-wise LearningMyeongjang Pyeon, Jihwan Moon, Taeyoung Hahn, Gunhee Kim. [doi]
- Effective Abstract Reasoning with Dual-Contrast NetworkTao Zhuo, Mohan S. Kankanhalli. [doi]
- Using latent space regression to analyze and leverage compositionality in GANsLucy Chai, Jonas Wulff, Phillip Isola. [doi]
- CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language UnderstandingYanru Qu, Dinghan Shen, Yelong Shen, Sandra Sajeev, Weizhu Chen, Jiawei Han 0001. [doi]
- Gradient Origin NetworksSam Bond-Taylor, Chris G. Willcocks. [doi]
- Fourier Neural Operator for Parametric Partial Differential EquationsZongyi Li, Nikola Borislavov Kovachki, Kamyar Azizzadenesheli, Burigede Liu, Kaushik Bhattacharya, Andrew M. Stuart, Anima Anandkumar. [doi]
- Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-LearningDong-Bok Lee, Dongchan Min, Seanie Lee, Sung Ju Hwang. [doi]
- SALD: Sign Agnostic Learning with DerivativesMatan Atzmon, Yaron Lipman. [doi]
- Adaptive Federated OptimizationSashank J. Reddi, Zachary Charles, Manzil Zaheer, Zachary Garrett, Keith Rush, Jakub Konecný, Sanjiv Kumar, Hugh Brendan McMahan. [doi]
- Meta Back-TranslationHieu Pham, Xinyi Wang, Yiming Yang, Graham Neubig. [doi]
- Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependenciesT. Konstantin Rusch, Siddhartha Mishra. [doi]
- Byzantine-Resilient Non-Convex Stochastic Gradient DescentZeyuan Allen Zhu, Faeze Ebrahimianghazani, Jerry Li 0001, Dan Alistarh. [doi]
- On the Transfer of Disentangled Representations in Realistic SettingsAndrea Dittadi, Frederik Träuble, Francesco Locatello, Manuel Wuthrich, Vaibhav Agrawal, Ole Winther, Stefan Bauer, Bernhard Schölkopf. [doi]
- My Body is a Cage: the Role of Morphology in Graph-Based Incompatible ControlVitaly Kurin, Maximilian Igl, Tim Rocktäschel, Wendelin Boehmer, Shimon Whiteson. [doi]
- Improving Transformation Invariance in Contrastive Representation LearningAdam Foster, Rattana Pukdee, Tom Rainforth. [doi]
- CompOFA - Compound Once-For-All Networks for Faster Multi-Platform DeploymentManas Sahni, Shreya Varshini, Alind Khare, Alexey Tumanov. [doi]
- GraphCodeBERT: Pre-training Code Representations with Data FlowDaya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie Liu 0001, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, Michele Tufano, Shao Kun Deng, Colin B. Clement, Dawn Drain, Neel Sundaresan, Jian Yin 0001, Daxin Jiang, Ming Zhou 0001. [doi]
- Auto Seg-Loss: Searching Metric Surrogates for Semantic SegmentationHao Li, Chenxin Tao, Xizhou Zhu, Xiaogang Wang, Gao Huang, Jifeng Dai. [doi]
- Online Adversarial Purification based on Self-supervised LearningChanghao Shi, Chester Holtz, Gal Mishne. [doi]
- Overfitting for Fun and Profit: Instance-Adaptive Data CompressionTies van Rozendaal, Iris A. M. Huijben, Taco Cohen. [doi]
- Adversarial score matching and improved sampling for image generationAlexia Jolicoeur-Martineau, Rémi Piché-Taillefer, Ioannis Mitliagkas, Remi Tachet des Combes. [doi]
- Parameter-Based Value FunctionsFrancesco Faccio, Louis Kirsch, Jürgen Schmidhuber. [doi]
- Dual-mode ASR: Unify and Improve Streaming ASR with Full-context ModelingJiahui Yu, Wei Han, Anmol Gulati, Chung-Cheng Chiu, Bo Li, Tara N. Sainath, Yonghui Wu, Ruoming Pang. [doi]
- Neural Thompson SamplingWeitong Zhang, Dongruo Zhou, Lihong Li 0001, Quanquan Gu. [doi]
- Communication in Multi-Agent Reinforcement Learning: Intention SharingWoojun Kim, Jongeui Park, Youngchul Sung. [doi]
- Semantic Re-tuning with Contrastive TensionFredrik Carlsson, Amaru Cuba Gyllensten, Evangelia Gogoulou, Erik Ylipää Hellqvist, Magnus Sahlgren. [doi]
- Score-Based Generative Modeling through Stochastic Differential EquationsYang Song 0011, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole. [doi]
- Return-Based Contrastive Representation Learning for Reinforcement LearningGuoqing Liu, Chuheng Zhang, Li Zhao, Tao Qin, Jinhua Zhu, Jian Li, Nenghai Yu, Tie-Yan Liu. [doi]
- On the geometry of generalization and memorization in deep neural networksCory Stephenson, Suchismita Padhy, Abhinav Ganesh, Yue Hui, Hanlin Tang, SueYeon Chung. [doi]
- Human-Level Performance in No-Press Diplomacy via Equilibrium SearchJonathan Gray, Adam Lerer, Anton Bakhtin, Noam Brown. [doi]
- On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization AnalysisZhong Li, Jiequn Han, Weinan E, Qianxiao Li. [doi]
- Contrastive Learning with Hard Negative SamplesJoshua David Robinson, Ching-Yao Chuang, Suvrit Sra, Stefanie Jegelka. [doi]
- Learning Reasoning Paths over Semantic Graphs for Video-grounded DialoguesHung Le, Nancy F. Chen, Steven C. H. Hoi. [doi]
- Spatio-Temporal Graph Scattering TransformChao Pan, Siheng Chen, Antonio Ortega. [doi]
- Monotonic Kronecker-Factored LatticeWilliam Taylor Bakst, Nobuyuki Morioka, Erez Louidor. [doi]
- DDPNOpt: Differential Dynamic Programming Neural OptimizerGuan-Horng Liu, Tianrong Chen, Evangelos A. Theodorou. [doi]
- Physics-aware, probabilistic model order reduction with guaranteed stabilitySebastian Kaltenbach, Phaedon-Stelios Koutsourelakis. [doi]
- Emergent Symbols through Binding in External MemoryTaylor Whittington Webb, Ishan Sinha, Jonathan D. Cohen 0003. [doi]
- Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight MasksRóbert Csordás, Sjoerd van Steenkiste, Jürgen Schmidhuber. [doi]
- Do 2D GANs Know 3D Shape? Unsupervised 3D Shape Reconstruction from 2D Image GANsXingang Pan, Bo Dai, Ziwei Liu, Chen Change Loy, Ping Luo. [doi]
- Distributed Momentum for Byzantine-resilient Stochastic Gradient DescentEl Mahdi El Mhamdi, Rachid Guerraoui, Sébastien Rouault. [doi]
- In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised LearningMamshad Nayeem Rizve, Kevin Duarte, Yogesh Singh Rawat, Mubarak Shah. [doi]
- Interpretable Models for Granger Causality Using Self-explaining Neural NetworksRicards Marcinkevics, Julia E. Vogt. [doi]
- On the Bottleneck of Graph Neural Networks and its Practical ImplicationsUri Alon 0002, Eran Yahav. [doi]
- Learning Mesh-Based Simulation with Graph NetworksTobias Pfaff, Meire Fortunato, Alvaro Sanchez-Gonzalez, Peter W. Battaglia. [doi]
- IOT: Instance-wise Layer Reordering for Transformer StructuresJinhua Zhu, Lijun Wu, Yingce Xia, Shufang Xie 0003, Tao Qin, Wengang Zhou, Houqiang Li, Tie-Yan Liu. [doi]
- Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex OptimizationChin-Wei Huang, Ricky T. Q. Chen, Christos Tsirigotis, Aaron C. Courville. [doi]
- Neural Jump Ordinary Differential Equations: Consistent Continuous-Time Prediction and FilteringCalypso Herrera, Florian Krach, Josef Teichmann. [doi]
- Linear Mode Connectivity in Multitask and Continual LearningSeyed-Iman Mirzadeh, Mehrdad Farajtabar, Dilan Görür, Razvan Pascanu, Hassan Ghasemzadeh 0001. [doi]
- Evolving Reinforcement Learning AlgorithmsJohn D. Co-Reyes, Yingjie Miao, Daiyi Peng, Esteban Real, Quoc V. Le, Sergey Levine, Honglak Lee, Aleksandra Faust. [doi]
- Network Pruning That Matters: A Case Study on Retraining VariantsDuong Hoang Le, Binh-Son Hua. [doi]
- SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better RegularizationA. F. M. Shahab Uddin, Mst. Sirazam Monira, Wheemyung Shin, TaeChoong Chung, Sung-Ho Bae. [doi]
- Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff PerspectiveHelong Zhou, Liangchen Song, Jiajie Chen, Ye Zhou, Guoli Wang, Junsong Yuan, Qian Zhang. [doi]
- When Do Curricula Work?Xiaoxia Wu, Ethan Dyer, Behnam Neyshabur. [doi]
- ARMOURED: Adversarially Robust MOdels using Unlabeled data by REgularizing DiversityKangkang Lu, Cuong Manh Nguyen, Xun Xu, Kiran Chari, Yu Jing Goh, Chuan-Sheng Foo. [doi]
- Planning from Pixels using Inverse Dynamics ModelsKeiran Paster, Sheila A. McIlraith, Jimmy Ba. [doi]
- Layer-adaptive Sparsity for the Magnitude-based PruningJaeho Lee, Sejun Park, Sangwoo Mo, Sungsoo Ahn, Jinwoo Shin. [doi]
- Taking Notes on the Fly Helps Language Pre-TrainingQiyu Wu 0001, Chen Xing, Yatao Li, Guolin Ke, Di He, Tie-Yan Liu. [doi]
- Expressive Power of Invariant and Equivariant Graph Neural NetworksWaiss Azizian, Marc Lelarge. [doi]
- Multiplicative Filter NetworksRizal Fathony, Anit Kumar Sahu, Devin Willmott, J. Zico Kolter. [doi]
- Group Equivariant Generative Adversarial NetworksNeel Dey, Antong Chen, Soheil Ghafurian. [doi]
- Interpreting Graph Neural Networks for NLP With Differentiable Edge MaskingMichael Sejr Schlichtkrull, Nicola De Cao, Ivan Titov. [doi]
- Training independent subnetworks for robust predictionMarton Havasi, Rodolphe Jenatton, Stanislav Fort, Jeremiah Zhe Liu, Jasper Snoek, Balaji Lakshminarayanan, Andrew Mingbo Dai, Dustin Tran. [doi]
- Counterfactual Generative NetworksAxel Sauer, Andreas Geiger 0001. [doi]
- FastSpeech 2: Fast and High-Quality End-to-End Text to SpeechYi Ren 0006, Chenxu Hu, Xu Tan 0003, Tao Qin, Sheng Zhao, Zhou Zhao, Tie-Yan Liu. [doi]
- Deep Partition Aggregation: Provable Defenses against General Poisoning AttacksAlexander Levine 0001, Soheil Feizi. [doi]
- Mind the Pad - CNNs Can Develop Blind SpotsBilal Alsallakh, Narine Kokhlikyan, Vivek Miglani, Jun Yuan, Orion Reblitz-Richardson. [doi]
- Learning to Set Waypoints for Audio-Visual NavigationChangan Chen, Sagnik Majumder, Ziad Al-Halah, Ruohan Gao, Santhosh Kumar Ramakrishnan, Kristen Grauman. [doi]
- Learning Hyperbolic Representations of Topological FeaturesPanagiotis Kyriakis, Iordanis Fostiropoulos, Paul Bogdan. [doi]
- Random Feature AttentionHao Peng, Nikolaos Pappas 0002, Dani Yogatama, Roy Schwartz 0001, Noah A. Smith, Lingpeng Kong. [doi]
- Diverse Video Generation using a Gaussian Process TriggerGaurav Shrivastava, Abhinav Shrivastava. [doi]
- Bowtie Networks: Generative Modeling for Joint Few-Shot Recognition and Novel-View SynthesisZhipeng Bao, Yu-Xiong Wang, Martial Hebert. [doi]
- Global Convergence of Three-layer Neural Networks in the Mean Field RegimeHuy Tuan Pham, Phan-Minh Nguyen. [doi]
- Practical Massively Parallel Monte-Carlo Tree Search Applied to Molecular DesignXiufeng Yang, Tanuj kr Aasawat, Kazuki Yoshizoe. [doi]
- Pruning Neural Networks at Initialization: Why Are We Missing the Mark?Jonathan Frankle, Gintare Karolina Dziugaite, Daniel Roy 0001, Michael Carbin. [doi]
- CaPC Learning: Confidential and Private Collaborative LearningChristopher A. Choquette-Choo, Natalie Dullerud, Adam Dziedzic, Yunxiang Zhang, Somesh Jha, Nicolas Papernot, Xiao Wang. [doi]
- Faster Binary Embeddings for Preserving Euclidean DistancesJinjie Zhang, Rayan Saab. [doi]
- Learning from Demonstration with Weakly Supervised DisentanglementYordan Hristov, Subramanian Ramamoorthy. [doi]
- Prototypical Representation Learning for Relation ExtractionNing Ding, XiaoBin Wang, Yao Fu, Guangwei Xu, Rui Wang, Pengjun Xie, Ying Shen, Fei Huang, Hai-Tao Zheng, Rui Zhang. [doi]
- Graph Coarsening with Neural NetworksChen Cai, DingKang Wang, Yusu Wang. [doi]
- EigenGame: PCA as a Nash EquilibriumIan M. Gemp, Brian McWilliams, Claire Vernade, Thore Graepel. [doi]
- Intraclass clustering: an implicit learning ability that regularizes DNNsSimon Carbonnelle, Christophe De Vleeschouwer. [doi]
- Data-Efficient Reinforcement Learning with Self-Predictive RepresentationsMax Schwarzer, Ankesh Anand, Rishab Goel, R. Devon Hjelm, Aaron C. Courville, Philip Bachman. [doi]
- Learning Long-term Visual Dynamics with Region Proposal Interaction NetworksHaozhi Qi, Xiaolong Wang, Deepak Pathak, Yi Ma 0001, Jitendra Malik. [doi]
- Adaptive Universal Generalized PageRank Graph Neural NetworkEli Chien, Jianhao Peng, Pan Li 0005, Olgica Milenkovic. [doi]
- On the Universality of the Double Descent Peak in Ridgeless RegressionDavid Holzmüller. [doi]
- Conditional Generative Modeling via Learning the Latent SpaceSameera Ramasinghe, Kanchana Nisal Ranasinghe, Salman Khan, Nick Barnes, Stephen Gould. [doi]
- Few-Shot Learning via Learning the Representation, ProvablySimon Shaolei Du, Wei Hu, Sham M. Kakade, Jason D. Lee, Qi Lei. [doi]
- Rethinking Positional Encoding in Language Pre-trainingGuolin Ke, Di He, Tie-Yan Liu. [doi]
- Linear Last-iterate Convergence in Constrained Saddle-point OptimizationChen-Yu Wei, Chung-wei Lee, Mengxiao Zhang, Haipeng Luo. [doi]
- Neural Networks for Learning Counterfactual G-Invariances from Single EnvironmentsS. Chandra Mouli, Bruno Ribeiro 0001. [doi]
- Generalized Multimodal ELBOThomas M. Sutter, Imant Daunhawer, Julia E. Vogt. [doi]
- How Benign is Benign Overfitting ?Amartya Sanyal, Puneet K. Dokania, Varun Kanade, Philip H. S. Torr. [doi]
- Private Post-GAN BoostingMarcel Neunhoeffer, Steven Wu 0001, Cynthia Dwork. [doi]
- Sparse Quantized Spectral ClusteringZhenyu Liao, Romain Couillet, Michael W. Mahoney. [doi]
- Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNsJonathan Frankle, David J. Schwab, Ari S. Morcos. [doi]
- Estimating informativeness of samples with Smooth Unique InformationHrayr Harutyunyan, Alessandro Achille, Giovanni Paolini, Orchid Majumder, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto. [doi]
- MODALS: Modality-agnostic Automated Data Augmentation in the Latent SpaceTsz-Him Cheung, Dit-Yan Yeung. [doi]
- FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior RegularizationLanqing Li, Rui Yang, Dijun Luo. [doi]
- Hopper: Multi-hop Transformer for Spatiotemporal ReasoningHonglu Zhou, Asim Kadav, Farley Lai, Alexandru Niculescu-Mizil, Martin Renqiang Min, Mubbasir Kapadia, Hans Peter Graf. [doi]
- Share or Not? Learning to Schedule Language-Specific Capacity for Multilingual TranslationBiao Zhang, Ankur Bapna, Rico Sennrich, Orhan Firat. [doi]
- Aligning AI With Shared Human ValuesDan Hendrycks, Collin Burns, Steven Basart, Andrew Critch, Jerry Li 0001, Dawn Song, Jacob Steinhardt. [doi]
- Topology-Aware Segmentation Using Discrete Morse TheoryXiaoling Hu, Yusu Wang, Fuxin Li, Dimitris Samaras, Chao Chen. [doi]
- Separation and Concentration in Deep NetworksJohn Zarka, Florentin Guth, Stéphane Mallat. [doi]
- Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue SystemJianhong Wang, Yuan Zhang, Tae-Kyun Kim, Yunjie Gu. [doi]
- PAC Confidence Predictions for Deep Neural Network ClassifiersSangdon Park, Shuo Li, Insup Lee, Osbert Bastani. [doi]
- Learning Manifold Patch-Based Representations of Man-Made ShapesDmitriy Smirnov 0001, Mikhail Bessmeltsev, Justin Solomon 0001. [doi]
- Sharpness-aware Minimization for Efficiently Improving GeneralizationPierre Foret, Ariel Kleiner, Hossein Mobahi, Behnam Neyshabur. [doi]
- Adversarially Guided Actor-CriticYannis Flet-Berliac, Johan Ferret, Olivier Pietquin, Philippe Preux, Matthieu Geist. [doi]
- Regularized Inverse Reinforcement LearningWonseok Jeon, Chen-Yang Su, Paul Barde, Thang Doan, Derek Nowrouzezahrai, Joelle Pineau. [doi]
- Targeted Attack against Deep Neural Networks via Flipping Limited Weight BitsJiawang Bai, Baoyuan Wu, Yong Zhang, Yiming Li, Zhifeng Li 0003, Shu-Tao Xia. [doi]
- Long-tailed Recognition by Routing Diverse Distribution-Aware ExpertsXudong Wang, Long Lian, Zhongqi Miao, Ziwei Liu 0002, Stella Yu. [doi]
- Large Scale Image Completion via Co-Modulated Generative Adversarial NetworksShengyu Zhao, Jonathan Cui, Yilun Sheng, Yue Dong, Xiao Liang, Eric I-Chao Chang, Yan Xu. [doi]
- The Importance of Pessimism in Fixed-Dataset Policy OptimizationJacob Buckman, Carles Gelada, Marc G. Bellemare. [doi]
- Text Generation by Learning from DemonstrationsRichard Yuanzhe Pang, He He 0001. [doi]
- Implicit Normalizing FlowsCheng Lu, Jianfei Chen 0001, Chongxuan Li, Qiuhao Wang, Jun Zhu. [doi]
- Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable ModelsJustin Bayer, Maximilian Soelch, Atanas Mirchev, Baris Kayalibay, Patrick van der Smagt. [doi]
- Linear Convergent Decentralized Optimization with CompressionXiaorui Liu, Yao Li, Rongrong Wang, Jiliang Tang, Ming Yan 0006. [doi]
- Incorporating Symmetry into Deep Dynamics Models for Improved GeneralizationRui Wang, Robin Walters, Rose Yu. [doi]
- Capturing Label Characteristics in VAEsTom Joy, Sebastian M. Schmon, Philip H. S. Torr, Siddharth Narayanaswamy, Tom Rainforth. [doi]
- Characterizing signal propagation to close the performance gap in unnormalized ResNetsAndrew Brock, Soham De, Samuel L. Smith. [doi]
- MALI: A memory efficient and reverse accurate integrator for Neural ODEsJuntang Zhuang, Nicha C. Dvornek, Sekhar Tatikonda, James S. Duncan. [doi]
- Taming GANs with Lookahead-MinmaxTatjana Chavdarova, Matteo Pagliardini, Sebastian U. Stich, François Fleuret, Martin Jaggi. [doi]
- Shapley explainability on the data manifoldChristopher Frye, Damien de Mijolla, Tom Begley, Laurence Cowton, Megan Stanley, Ilya Feige. [doi]
- Shape or Texture: Understanding Discriminative Features in CNNsMd. Amirul Islam, Matthew Kowal, Patrick Esser, Sen Jia, Björn Ommer, Konstantinos G. Derpanis, Neil D. B. Bruce. [doi]
- Noise or Signal: The Role of Image Backgrounds in Object RecognitionKai Yuanqing Xiao, Logan Engstrom, Andrew Ilyas, Aleksander Madry. [doi]
- Anatomy of Catastrophic Forgetting: Hidden Representations and Task SemanticsVinay Venkatesh Ramasesh, Ethan Dyer, Maithra Raghu. [doi]
- Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman KernelsBin Xin Ru, Xingchen Wan, Xiaowen Dong 0001, Michael A. Osborne. [doi]
- Trajectory Prediction using Equivariant Continuous ConvolutionRobin Walters, Jinxi Li, Rose Yu. [doi]
- A Unified Approach to Interpreting and Boosting Adversarial TransferabilityXin Wang, Jie Ren, Shuyun Lin, Xiangming Zhu, Yisen Wang 0001, Quanshi Zhang. [doi]
- Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient DetectorsLinfeng Zhang, Kaisheng Ma. [doi]
- Self-Supervised Learning of Compressed Video RepresentationsYoungjae Yu, Sangho Lee, Gunhee Kim, Yale Song. [doi]
- Balancing Constraints and Rewards with Meta-Gradient D4PGDan A. Calian, Daniel J. Mankowitz, Tom Zahavy, Zhongwen Xu, Junhyuk Oh, Nir Levine, Timothy A. Mann. [doi]
- Learning Energy-Based Models by Diffusion Recovery LikelihoodRuiQi Gao, Yang Song, Ben Poole, Ying Nian Wu, Diederik P. Kingma. [doi]
- Adaptive and Generative Zero-Shot LearningYu-Ying Chou, Hsuan-Tien Lin, Tyng-Luh Liu. [doi]
- HW-NAS-Bench: Hardware-Aware Neural Architecture Search BenchmarkChaojian Li, Zhongzhi Yu, Yonggan Fu, Yongan Zhang, Yang Zhao, Haoran You, Qixuan Yu, Yue Wang 0036, Cong Hao, Yingyan Lin. [doi]
- Training GANs with Stronger Augmentations via Contrastive DiscriminatorJongheon Jeong, Jinwoo Shin. [doi]
- Initialization and Regularization of Factorized Neural LayersMikhail Khodak, Neil A. Tenenholtz, Lester Mackey, Nicolò Fusi. [doi]
- Improving Adversarial Robustness via Channel-wise Activation SuppressingYang Bai, Yuyuan Zeng, Yong Jiang, Shu-Tao Xia, Xingjun Ma, Yisen Wang 0001. [doi]
- Learning to live with Dale's principle: ANNs with separate excitatory and inhibitory unitsJonathan Cornford, Damjan Kalajdzievski, Marco Leite, Amélie Lamarquette, Dimitri Michael Kullmann, Blake Aaron Richards. [doi]
- Removing Undesirable Feature Contributions Using Out-of-Distribution DataSaehyung Lee, Changhwa Park, Hyungyu Lee, Jihun Yi, Jonghyun Lee 0004, Sungroh Yoon. [doi]
- Discovering Non-monotonic Autoregressive Orderings with Variational InferenceXuanlin Li, Brandon Trabucco, Dong Huk Park, Michael Luo, Sheng Shen, Trevor Darrell, Yang Gao 0029. [doi]
- DeepAveragers: Offline Reinforcement Learning By Solving Derived Non-Parametric MDPsAayam Kumar Shrestha, Stefan Lee, Prasad Tadepalli, Alan Fern. [doi]
- The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels MethodsLouis Thiry, Michael Arbel, Eugene Belilovsky, Edouard Oyallon. [doi]
- Deployment-Efficient Reinforcement Learning via Model-Based Offline OptimizationTatsuya Matsushima, Hiroki Furuta, Yutaka Matsuo, Ofir Nachum, Shixiang Gu. [doi]
- Deformable DETR: Deformable Transformers for End-to-End Object DetectionXizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, Jifeng Dai. [doi]
- MixKD: Towards Efficient Distillation of Large-scale Language ModelsKevin J. Liang, Weituo Hao, Dinghan Shen, Yufan Zhou, Weizhu Chen, Changyou Chen, Lawrence Carin. [doi]
- A Distributional Approach to Controlled Text GenerationMuhammad Khalifa, Hady ElSahar, Marc Dymetman. [doi]
- Trusted Multi-View ClassificationZongbo Han, Changqing Zhang, Huazhu Fu, Joey Tianyi Zhou. [doi]
- Provably robust classification of adversarial examples with detectionFatemeh Sheikholeslami, Ali Lotfi, J. Zico Kolter. [doi]
- UPDeT: Universal Multi-agent RL via Policy Decoupling with TransformersSiyi Hu, Fengda Zhu, Xiaojun Chang, Xiaodan Liang. [doi]
- CPR: Classifier-Projection Regularization for Continual LearningSungmin Cha, Hsiang Hsu, Taebaek Hwang, Flávio P. Calmon, Taesup Moon. [doi]
- Unsupervised Discovery of 3D Physical Objects from VideoYilun Du, Kevin A. Smith, Tomer Ullman, Joshua B. Tenenbaum, Jiajun Wu 0001. [doi]
- DOP: Off-Policy Multi-Agent Decomposed Policy GradientsYihan Wang, Beining Han, Tonghan Wang 0001, Heng Dong, Chongjie Zhang. [doi]
- Discrete Graph Structure Learning for Forecasting Multiple Time SeriesChao Shang, Jie Chen 0007, Jinbo Bi. [doi]
- DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial EstimationAlexandre Ramé, Matthieu Cord. [doi]
- NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-end Learning and ControlIoannis Exarchos, Marcus Aloysius Pereira, Ziyi Wang, Evangelos A. Theodorou. [doi]
- VTNet: Visual Transformer Network for Object Goal NavigationHeming Du, Xin Yu, Liang Zheng 0001. [doi]
- Evaluation of Similarity-based ExplanationsKazuaki Hanawa, Sho Yokoi, Satoshi Hara 0001, Kentaro Inui. [doi]
- Spatial Dependency Networks: Neural Layers for Improved Generative Image ModelingÐorðe Miladinovic, Aleksandar Stanic, Stefan Bauer, Jürgen Schmidhuber, Joachim M. Buhmann. [doi]
- Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets?Zhiyuan Li 0005, Yi Zhang, Sanjeev Arora. [doi]
- How Does Mixup Help With Robustness and Generalization?Linjun Zhang, Zhun Deng, Kenji Kawaguchi, Amirata Ghorbani, James Zou 0001. [doi]
- Identifying Physical Law of Hamiltonian Systems via Meta-LearningSeungjun Lee, Haesang Yang, Woojae Seong. [doi]
- BERTology Meets Biology: Interpreting Attention in Protein Language ModelsJesse Vig, Ali Madani, Lav R. Varshney, Caiming Xiong, Richard Socher, Nazneen Fatema Rajani. [doi]
- Neural Spatio-Temporal Point ProcessesRicky T. Q. Chen, Brandon Amos, Maximilian Nickel. [doi]
- Learning Neural Generative Dynamics for Molecular Conformation GenerationMinkai Xu, Shitong Luo, Yoshua Bengio, Jian Peng, Jian Tang. [doi]
- Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse CodingDavid A. Klindt, Lukas Schott, Yash Sharma, Ivan Ustyuzhaninov, Wieland Brendel, Matthias Bethge, Dylan M. Paiton. [doi]
- On the Critical Role of Conventions in Adaptive Human-AI CollaborationAndy Shih, Arjun Sawhney, Jovana Kondic, Stefano Ermon, Dorsa Sadigh. [doi]
- Generalization in data-driven models of primary visual cortexKonstantin-Klemens Lurz, Mohammad Bashiri, Konstantin Willeke, Akshay Jagadish, Eric Wang, Edgar Y. Walker, Santiago A. Cadena, Taliah Muhammad, Erick Cobos, Andreas S. Tolias, Alexander S. Ecker, Fabian H. Sinz. [doi]
- RODE: Learning Roles to Decompose Multi-Agent TasksTonghan Wang 0001, Tarun Gupta 0002, Anuj Mahajan, Bei Peng, Shimon Whiteson, Chongjie Zhang. [doi]
- Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' RuleShuhei Kurita, KyungHyun Cho. [doi]
- Does enhanced shape bias improve neural network robustness to common corruptions?Chaithanya Kumar Mummadi, Ranjitha Subramaniam, Robin Hutmacher, Julien Vitay, Volker Fischer 0003, Jan Hendrik Metzen. [doi]
- ChipNet: Budget-Aware Pruning with Heaviside Continuous ApproximationsRishabh Tiwari, Udbhav Bamba, Arnav Chavan, Deepak K. Gupta. [doi]
- Graph Information Bottleneck for Subgraph RecognitionJunchi Yu, Tingyang Xu, Yu Rong, Yatao Bian, JunZhou Huang, Ran He. [doi]
- The geometry of integration in text classification RNNsKyle Aitken, Vinay Venkatesh Ramasesh, Ankush Garg, Yuan Cao, David Sussillo, Niru Maheswaranathan. [doi]
- Understanding the effects of data parallelism and sparsity on neural network trainingNamhoon Lee, Thalaiyasingam Ajanthan, Philip H. S. Torr, Martin Jaggi. [doi]
- Noise against noise: stochastic label noise helps combat inherent label noisePengfei Chen, Guangyong Chen, Junjie Ye, Jingwei Zhao, Pheng-Ann Heng. [doi]
- Learning with Feature-Dependent Label Noise: A Progressive ApproachYikai Zhang, Songzhu Zheng, Pengxiang Wu, Mayank Goswami 0001, Chao Chen 0012. [doi]
- PseudoSeg: Designing Pseudo Labels for Semantic SegmentationYuliang Zou, Zizhao Zhang, Han Zhang, Chun-Liang Li, Xiao Bian, Jia-Bin Huang, Tomas Pfister. [doi]
- MONGOOSE: A Learnable LSH Framework for Efficient Neural Network TrainingBeidi Chen, Zichang Liu, Binghui Peng, Zhaozhuo Xu, Jonathan Lingjie Li, Tri Dao, Zhao Song 0002, Anshumali Shrivastava, Christopher Ré. [doi]
- Influence Estimation for Generative Adversarial NetworksNaoyuki Terashita, Hiroki Ohashi, Yuichi Nonaka, Takashi Kanemaru. [doi]
- Class Normalization for (Continual)? Generalized Zero-Shot LearningIvan Skorokhodov, Mohamed Elhoseiny. [doi]
- X2T: Training an X-to-Text Typing Interface with Online Learning from User FeedbackJensen Gao, Siddharth Reddy, Glen Berseth, Nicholas Hardy, Nikhilesh Natraj, Karunesh Ganguly, Anca Dragan, Sergey Levine. [doi]
- Generating Adversarial Computer Programs using Optimized ObfuscationsShashank Srikant, Sijia Liu 0001, Tamara Mitrovska, Shiyu Chang, Quanfu Fan, Gaoyuan Zhang, Una-May O'Reilly. [doi]
- Overparameterisation and worst-case generalisation: friend or foe?Aditya Krishna Menon, Ankit Singh Rawat, Sanjiv Kumar. [doi]
- Uncertainty in Gradient Boosting via EnsemblesAndrey Malinin, Liudmila Prokhorenkova, Aleksei Ustimenko. [doi]
- Theoretical Analysis of Self-Training with Deep Networks on Unlabeled DataColin Wei, Kendrick Shen, Yining Chen, Tengyu Ma. [doi]
- What are the Statistical Limits of Offline RL with Linear Function Approximation?Ruosong Wang, Dean P. Foster, Sham M. Kakade. [doi]
- Selectivity considered harmful: evaluating the causal impact of class selectivity in DNNsMatthew L. Leavitt, Ari S. Morcos. [doi]
- Learning What To Do by Simulating the PastDavid Lindner, Rohin Shah, Pieter Abbeel, Anca D. Dragan. [doi]
- GShard: Scaling Giant Models with Conditional Computation and Automatic ShardingDmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Maxim Krikun, Noam Shazeer, Zhifeng Chen. [doi]
- Generalized Variational Continual LearningNoel Loo, Siddharth Swaroop, Richard E. Turner. [doi]
- Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNsCheng Wang, Carolin Lawrence, Mathias Niepert. [doi]
- Solving Compositional Reinforcement Learning Problems via Task ReductionYunfei Li, Yilin Wu, Huazhe Xu, Xiaolong Wang 0004, Yi Wu. [doi]
- You Only Need Adversarial Supervision for Semantic Image SynthesisEdgar Schönfeld, Vadim Sushko, Dan Zhang 0017, Juergen Gall, Bernt Schiele, Anna Khoreva. [doi]
- BOIL: Towards Representation Change for Few-shot LearningJaehoon Oh, Hyungjun Yoo, ChangHwan Kim, Se-Young Yun. [doi]
- Learning Invariant Representations for Reinforcement Learning without ReconstructionAmy Zhang 0001, Rowan Thomas McAllister, Roberto Calandra, Yarin Gal, Sergey Levine. [doi]
- Self-supervised Learning from a Multi-view PerspectiveYao-Hung Hubert Tsai, Yue Wu 0001, Ruslan Salakhutdinov, Louis-Philippe Morency. [doi]
- Mapping the Timescale Organization of Neural Language ModelsHsiang-Yun Sherry Chien, Jinhan Zhang, Christopher J. Honey. [doi]
- Robust Reinforcement Learning on State Observations with Learned Optimal AdversaryHuan Zhang, Hongge Chen, Duane S. Boning, Cho-Jui Hsieh. [doi]
- CO2: Consistent Contrast for Unsupervised Visual Representation LearningChen Wei 0005, Huiyu Wang, Wei Shen 0002, Alan iL. uille. [doi]
- Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image SynthesisBingchen Liu, Yizhe Zhu, Kunpeng Song, Ahmed Elgammal. [doi]
- LambdaNetworks: Modeling long-range Interactions without AttentionIrwan Bello. [doi]
- Clairvoyance: A Pipeline Toolkit for Medical Time SeriesDaniel Jarrett, Jinsung Yoon, Ioana Bica, Zhaozhi Qian, Ari Ercole, Mihaela van der Schaar. [doi]
- Async-RED: A Provably Convergent Asynchronous Block Parallel Stochastic Method using Deep Denoising PriorsYu Sun 0022, Jiaming Liu, Yiran Sun, Brendt Wohlberg, Ulugbek Kamilov. [doi]
- Grounding Physical Concepts of Objects and Events Through Dynamic Visual ReasoningZhenfang Chen, Jiayuan Mao, Jiajun Wu 0001, Kwan-Yee Kenneth Wong, Joshua B. Tenenbaum, Chuang Gan. [doi]
- Representing Partial Programs with Blended Abstract SemanticsMaxwell I. Nye, Yewen Pu, Matthew Bowers, Jacob Andreas, Joshua B. Tenenbaum, Armando Solar-Lezama. [doi]
- Understanding the failure modes of out-of-distribution generalizationVaishnavh Nagarajan, Anders Andreassen, Behnam Neyshabur. [doi]
- Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less DataJonathan Pilault, Amine Elhattami, Christopher J. Pal. [doi]
- EEC: Learning to Encode and Regenerate Images for Continual LearningAli Ayub, Alan R. Wagner. [doi]
- Neural Approximate Sufficient Statistics for Implicit ModelsYanzhi Chen, Dinghuai Zhang, Michael U. Gutmann, Aaron C. Courville, Zhanxing Zhu. [doi]
- Clustering-friendly Representation Learning via Instance Discrimination and Feature DecorrelationYaling Tao, Kentaro Takagi, Kouta Nakata. [doi]
- Support-set bottlenecks for video-text representation learningMandela Patrick, Po-Yao Huang 0001, Yuki Markus Asano, Florian Metze, Alexander G. Hauptmann, João F. Henriques, Andrea Vedaldi. [doi]
- DrNAS: Dirichlet Neural Architecture SearchXiangning Chen, Ruochen Wang, Minhao Cheng, Xiaocheng Tang, Cho-Jui Hsieh. [doi]
- Estimating Lipschitz constants of monotone deep equilibrium modelsChirag Pabbaraju, Ezra Winston, J. Zico Kolter. [doi]
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov 0003, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani 0001, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby. [doi]
- Effective Distributed Learning with Random Features: Improved Bounds and AlgorithmsYong Liu 0018, Jiankun Liu, Shuqiang Wang. [doi]
- The Deep Bootstrap Framework: Good Online Learners are Good Offline GeneralizersPreetum Nakkiran, Behnam Neyshabur, Hanie Sedghi. [doi]
- Fuzzy Tiling Activations: A Simple Approach to Learning Sparse Representations OnlineYangchen Pan, Kirby Banman, Martha White. [doi]
- Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement LearningRishabh Agarwal, Marlos C. Machado, Pablo Samuel Castro, Marc G. Bellemare. [doi]
- Information Laundering for Model PrivacyXinran Wang, Yu Xiang, Jun Gao, Jie Ding 0002. [doi]
- Deep Equals Shallow for ReLU Networks in Kernel RegimesAlberto Bietti, Francis R. Bach. [doi]
- Neural representation and generation for RNA secondary structuresZichao Yan, William L. Hamilton, Mathieu Blanchette. [doi]
- WrapNet: Neural Net Inference with Ultra-Low-Precision ArithmeticRenkun Ni, Hong-Min Chu, Oscar Castañeda, Ping-Yeh Chiang, Christoph Studer, Tom Goldstein. [doi]
- VAEBM: A Symbiosis between Variational Autoencoders and Energy-based ModelsZhisheng Xiao, Karsten Kreis, Jan Kautz, Arash Vahdat. [doi]
- Anchor & Transform: Learning Sparse Embeddings for Large VocabulariesPaul Pu Liang, Manzil Zaheer, Yuan Wang, Amr Ahmed. [doi]
- Undistillable: Making A Nasty Teacher That CANNOT teach studentsHaoyu Ma, Tianlong Chen, Ting-Kuei Hu, Chenyu You, Xiaohui Xie, Zhangyang Wang. [doi]
- Dataset Meta-Learning from Kernel Ridge-RegressionTimothy Nguyen, Zhourong Chen, Jaehoon Lee. [doi]
- Scalable Bayesian Inverse Reinforcement LearningAlex James Chan, Mihaela van der Schaar. [doi]
- Meta-learning Symmetries by ReparameterizationAllan Zhou, Tom Knowles, Chelsea Finn. [doi]
- Concept Learners for Few-Shot LearningKaidi Cao, Maria Brbic, Jure Leskovec. [doi]
- Activation-level uncertainty in deep neural networksPablo Morales-Alvarez, Daniel Hernández-Lobato, Rafael Molina 0001, José Miguel Hernández-Lobato. [doi]
- The Role of Momentum Parameters in the Optimal Convergence of Adaptive Polyak's Heavy-ball MethodsWei Tao, Sheng Long, Gaowei Wu, Qing Tao. [doi]
- Integrating Categorical Semantics into Unsupervised Domain TranslationSamuel Lavoie-Marchildon, Faruk Ahmed, Aaron C. Courville. [doi]
- Learning Energy-Based Generative Models via Coarse-to-Fine Expanding and SamplingYang Zhao, Jianwen Xie, Ping Li. [doi]
- Robust Overfitting may be mitigated by properly learned smootheningTianlong Chen, Zhenyu Zhang, Sijia Liu 0001, Shiyu Chang, Zhangyang Wang. [doi]
- Group Equivariant Conditional Neural ProcessesMakoto Kawano, Wataru Kumagai, Akiyoshi Sannai, Yusuke Iwasawa, Yutaka Matsuo. [doi]
- Simple Spectral Graph ConvolutionHao Zhu, Piotr Koniusz. [doi]
- Graph-Based Continual LearningBinh Tang, David S. Matteson. [doi]
- Minimum Width for Universal ApproximationSejun Park, Chulhee Yun, Jaeho Lee, Jinwoo Shin. [doi]
- Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with 1/n ParametersAston Zhang, Yi Tay, Shuai Zhang 0007, Alvin Chan, Anh Tuan Luu, Siu Cheung Hui, Jie Fu. [doi]
- Collective Robustness Certificates: Exploiting Interdependence in Graph Neural NetworksJan Schuchardt, Aleksandar Bojchevski, Johannes Klicpera, Stephan Günnemann. [doi]
- Anytime Sampling for Autoregressive Models via Ordered AutoencodingYilun Xu, Yang Song, Sahaj Garg, Linyuan Gong, Rui Shu, Aditya Grover, Stefano Ermon. [doi]
- Personalized Federated Learning with First Order Model OptimizationMichael Zhang, Karan Sapra, Sanja Fidler, Serena Yeung, Jose M. Alvarez. [doi]
- How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks?Zixiang Chen, Yuan Cao 0006, Difan Zou, Quanquan Gu. [doi]
- On Position Embeddings in BERTBenyou Wang, Lifeng Shang, Christina Lioma, Xin Jiang, Hao Yang, Qun Liu, Jakob Grue Simonsen. [doi]
- Control-Aware Representations for Model-based Reinforcement LearningBrandon Cui, Yinlam Chow, Mohammad Ghavamzadeh. [doi]
- Deep Repulsive Clustering of Ordered Data Based on Order-Identity DecompositionSeon-Ho Lee, Chang-Su Kim. [doi]
- On Dyadic Fairness: Exploring and Mitigating Bias in Graph ConnectionsPeizhao Li, Yifei Wang, Han Zhao 0002, Pengyu Hong, Hongfu Liu. [doi]
- Scalable Learning and MAP Inference for Nonsymmetric Determinantal Point ProcessesMike Gartrell, Insu Han, Elvis Dohmatob, Jennifer Gillenwater, Victor-Emmanuel Brunel. [doi]
- Learning Parametrised Graph Shift OperatorsGeorge Dasoulas, Johannes F. Lutzeyer, Michalis Vazirgiannis. [doi]
- DeLighT: Deep and Light-weight TransformerSachin Mehta, Marjan Ghazvininejad, Srinivasan Iyer, Luke Zettlemoyer, Hannaneh Hajishirzi. [doi]
- End-to-End Egospheric Spatial MemoryDaniel James Lenton, Stephen James, Ronald Clark, Andrew J. Davison. [doi]
- Domain-Robust Visual Imitation Learning with Mutual Information ConstraintsEdoardo Cetin, Oya Çeliktutan. [doi]
- Large Associative Memory Problem in Neurobiology and Machine LearningDmitry Krotov, John J. Hopfield. [doi]
- ANOCE: Analysis of Causal Effects with Multiple Mediators via Constrained Structural LearningHengrui Cai, Rui Song, Wenbin Lu. [doi]
- Model Patching: Closing the Subgroup Performance Gap with Data AugmentationKaran Goel, Albert Gu, Yixuan Li, Christopher Ré. [doi]
- Exploring Balanced Feature Spaces for Representation LearningBingyi Kang, Yu Li, Sa Xie, Zehuan Yuan, Jiashi Feng. [doi]
- Revisiting Few-sample BERT Fine-tuningTianyi Zhang 0007, Felix Wu, Arzoo Katiyar, Kilian Q. Weinberger, Yoav Artzi. [doi]
- Structured Prediction as Translation between Augmented Natural LanguagesGiovanni Paolini, Ben Athiwaratkun, Jason Krone, Jie Ma, Alessandro Achille, Rishita Anubhai, Cicero Nogueira dos Santos, Bing Xiang, Stefano Soatto. [doi]
- Efficient Inference of Flexible Interaction in Spiking-neuron NetworksFeng Zhou, Yixuan Zhang, Jun Zhu. [doi]
- Prototypical Contrastive Learning of Unsupervised RepresentationsJunnan Li 0001, Pan Zhou, Caiming Xiong, Steven C. H. Hoi. [doi]
- Disentangled Recurrent Wasserstein AutoencoderJun Han, Martin Renqiang Min, Ligong Han, Li Erran Li, Xuan Zhang. [doi]
- Autoregressive Entity RetrievalNicola De Cao, Gautier Izacard, Sebastian Riedel 0001, Fabio Petroni. [doi]
- Directed Acyclic Graph Neural NetworksVeronika Thost, Jie Chen 0007. [doi]
- Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text RetrievalLee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul N. Bennett, Junaid Ahmed, Arnold Overwijk. [doi]
- How Neural Networks Extrapolate: From Feedforward to Graph Neural NetworksKeyulu Xu, Mozhi Zhang, Jingling Li, Simon Shaolei Du, Ken-ichi Kawarabayashi, Stefanie Jegelka. [doi]
- Iterative Empirical Game Solving via Single Policy Best ResponseMax Olan Smith, Thomas Anthony, Michael P. Wellman. [doi]
- C-Learning: Horizon-Aware Cumulative Accessibility EstimationPanteha Naderian, Gabriel Loaiza-Ganem, Harry J. Braviner, Anthony L. Caterini, Jesse C. Cresswell, Tong Li, Animesh Garg. [doi]
- On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong BaselinesMarius Mosbach, Maksym Andriushchenko, Dietrich Klakow. [doi]
- Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural NetworksShikuang Deng, Shi Gu. [doi]
- GraPPa: Grammar-Augmented Pre-Training for Table Semantic ParsingTao Yu 0009, Chien-Sheng Wu, Xi Victoria Lin, Bailin Wang, Yi Chern Tan, Xinyi Yang, Dragomir R. Radev, Richard Socher, Caiming Xiong. [doi]
- Towards Robustness Against Natural Language Word SubstitutionsXinshuai Dong, Anh Tuan Luu, Rongrong Ji, Hong Liu 0009. [doi]
- Calibration tests beyond classificationDavid Widmann, Fredrik Lindsten, Dave Zachariah. [doi]
- Geometry-aware Instance-reweighted Adversarial TrainingJingfeng Zhang, Jianing Zhu, Gang Niu 0001, Bo Han 0003, Masashi Sugiyama, Mohan S. Kankanhalli. [doi]
- Optimism in Reinforcement Learning with Generalized Linear Function ApproximationYining Wang 0001, Ruosong Wang, Simon Shaolei Du, Akshay Krishnamurthy. [doi]
- Ringing ReLUs: Harmonic Distortion Analysis of Nonlinear Feedforward NetworksChristian H. X. Ali Mehmeti-Göpel, David Hartmann, Michael Wand 0001. [doi]
- What Matters for On-Policy Deep Actor-Critic Methods? A Large-Scale StudyMarcin Andrychowicz, Anton Raichuk, Piotr Stanczyk, Manu Orsini, Sertan Girgin, Raphaël Marinier, Léonard Hussenot, Matthieu Geist, Olivier Pietquin, Marcin Michalski, Sylvain Gelly, Olivier Bachem. [doi]
- Large-width functional asymptotics for deep Gaussian neural networksDaniele Bracale, Stefano Favaro, Sandra Fortini, Stefano Peluchetti. [doi]
- Federated Learning via Posterior Averaging: A New Perspective and Practical AlgorithmsMaruan Al-Shedivat, Jennifer Gillenwater, Eric Xing, Afshin Rostamizadeh. [doi]
- DC3: A learning method for optimization with hard constraintsPriya L. Donti, David Rolnick, J. Zico Kolter. [doi]
- A Hypergradient Approach to Robust Regression without CorrespondenceYujia Xie, Yixiu Mao, Simiao Zuo, Hongteng Xu, Xiaojing Ye, Tuo Zhao, Hongyuan Zha. [doi]
- FedMix: Approximation of Mixup under Mean Augmented Federated LearningTehrim Yoon, Sumin Shin, Sung Ju Hwang, Eunho Yang. [doi]
- Self-Supervised Policy Adaptation during DeploymentNicklas Hansen, Rishabh Jangir, Yu Sun, Guillem Alenyà, Pieter Abbeel, Alexei A. Efros, Lerrel Pinto, Xiaolong Wang. [doi]
- Accurate Learning of Graph Representations with Graph Multiset PoolingJinheon Baek, Minki Kang, Sung Ju Hwang. [doi]
- Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted NetworkJames Diffenderfer, Bhavya Kailkhura. [doi]
- Interpreting and Boosting Dropout from a Game-Theoretic ViewHao Zhang, Sen Li, Yinchao Ma, Mingjie Li, Yichen Xie, Quanshi Zhang. [doi]
- Heating up decision boundaries: isocapacitory saturation, adversarial scenarios and generalization boundsBogdan Georgiev, Lukas Franken, Mayukh Mukherjee. [doi]
- Witches' Brew: Industrial Scale Data Poisoning via Gradient MatchingJonas Geiping, Liam H. Fowl, W. Ronny Huang, Wojciech Czaja, Gavin Taylor, Michael Moeller 0001, Tom Goldstein. [doi]
- Complex Query Answering with Neural Link PredictorsErik Arakelyan, Daniel Daza, Pasquale Minervini, Michael Cochez. [doi]
- In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution RobustnessSang Michael Xie, Ananya Kumar, Robbie Jones, Fereshte Khani, Tengyu Ma, Percy Liang. [doi]
- Correcting experience replay for multi-agent communicationSanjeevan Ahilan, Peter Dayan. [doi]
- Certify or Predict: Boosting Certified Robustness with Compositional ArchitecturesMark Niklas Müller, Mislav Balunovic, Martin T. Vechev. [doi]
- Multi-Class Uncertainty Calibration via Mutual Information Maximization-based BinningKanil Patel, William H. Beluch, Bin Yang, Michael Pfeiffer 0001, Dan Zhang. [doi]
- Lifelong Learning of Compositional StructuresJorge A. Mendez, Eric Eaton. [doi]
- Modeling the Second Player in Distributionally Robust OptimizationPaul Michel, Tatsunori Hashimoto, Graham Neubig. [doi]
- Effective and Efficient Vote Attack on Capsule NetworksJindong Gu, Baoyuan Wu, Volker Tresp. [doi]
- A Gradient Flow Framework For Analyzing Network PruningEkdeep Singh Lubana, Robert P. Dick. [doi]
- Orthogonalizing Convolutional Layers with the Cayley TransformAsher Trockman, J. Zico Kolter. [doi]
- Teaching with CommentariesAniruddh Raghu, Maithra Raghu, Simon Kornblith, David Duvenaud, Geoffrey E. Hinton. [doi]
- Single-Photon Image ClassificationThomas Fischbacher, Luciano Sbaiz. [doi]
- Emergent Road Rules In Multi-Agent Driving EnvironmentsAvik Pal, Jonah Philion, Yuan-Hong Liao, Sanja Fidler. [doi]
- Tomographic Auto-Encoder: Unsupervised Bayesian Recovery of Corrupted DataFrancesco Tonolini, Pablo Garcia-Moreno, Andreas Damianou, Roderick Murray-Smith. [doi]
- A Block Minifloat Representation for Training Deep Neural NetworksSean Fox, SeyedRamin Rasoulinezhad, Julian Faraone, David Boland, Philip H. W. Leong. [doi]
- Is Attention Better Than Matrix Decomposition?Zhengyang Geng, Meng-Hao Guo, Hongxu Chen, Xia Li, Ke Wei, Zhouchen Lin. [doi]
- Theoretical bounds on estimation error for meta-learningJames Lucas, Mengye Ren, Irene Raissa Kameni, Toniann Pitassi, Richard S. Zemel. [doi]
- AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the FlyYuchen Jin, Tianyi Zhou, Liangyu Zhao, Yibo Zhu, Chuanxiong Guo, Marco Canini, Arvind Krishnamurthy. [doi]
- Zero-Cost Proxies for Lightweight NASMohamed S. Abdelfattah, Abhinav Mehrotra, Lukasz Dudziak, Nicholas Donald Lane. [doi]
- BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network QuantizationHuanrui Yang, Lin Duan, Yiran Chen, Hai Li. [doi]
- FedBN: Federated Learning on Non-IID Features via Local Batch NormalizationXiaoxiao Li, Meirui Jiang, Xiaofei Zhang, Michael Kamp, Qi Dou. [doi]
- Wasserstein-2 Generative NetworksAlexander Korotin, Vage Egiazarian, Arip Asadulaev, Alexander Safin, Evgeny Burnaev. [doi]
- OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement LearningAnurag Ajay, Aviral Kumar, Pulkit Agrawal, Sergey Levine, Ofir Nachum. [doi]
- Economic Hyperparameter Optimization with Blended Search StrategyChi Wang 0001, Qingyun Wu, Silu Huang, Amin Saied. [doi]
- CPT: Efficient Deep Neural Network Training via Cyclic PrecisionYonggan Fu, Han Guo, Meng Li, Xin Yang, Yining Ding, Vikas Chandra, Yingyan Lin. [doi]
- Auxiliary Learning by Implicit DifferentiationAviv Navon, Idan Achituve, Haggai Maron, Gal Chechik, Ethan Fetaya. [doi]
- HyperGrid Transformers: Towards A Single Model for Multiple TasksYi Tay, Zhe Zhao, Dara Bahri, Donald Metzler, Da-Cheng Juan. [doi]
- NAS-Bench-ASR: Reproducible Neural Architecture Search for Speech RecognitionAbhinav Mehrotra, Alberto Gil C. P. Ramos, Sourav Bhattacharya, Lukasz Dudziak, Ravichander Vipperla, Thomas C. P. Chau, Mohamed S. Abdelfattah, Samin Ishtiaq, Nicholas Donald Lane. [doi]
- Selective Classification Can Magnify Disparities Across GroupsErik Jones, Shiori Sagawa, Pang Wei Koh, Ananya Kumar, Percy Liang. [doi]
- Generative Time-series Modeling with Fourier FlowsAhmed M. Alaa, Alex James Chan, Mihaela van der Schaar. [doi]
- Average-case Acceleration for Bilinear Games and Normal MatricesCarles Domingo-Enrich, Fabian Pedregosa, Damien Scieur. [doi]
- Evaluations and Methods for Explanation through Robustness AnalysisCheng-Yu Hsieh, Chih-Kuan Yeh, Xuanqing Liu, Pradeep Kumar Ravikumar, Seungyeon Kim, Sanjiv Kumar, Cho-Jui Hsieh. [doi]
- Calibration of Neural Networks using SplinesKartik Gupta, Amir Rahimi, Thalaiyasingam Ajanthan, Thomas Mensink, Cristian Sminchisescu, Richard Hartley 0001. [doi]
- Viewmaker Networks: Learning Views for Unsupervised Representation LearningAlex Tamkin, Mike Wu, Noah D. Goodman. [doi]
- Enforcing robust control guarantees within neural network policiesPriya L. Donti, Melrose Roderick, Mahyar Fazlyab, J. Zico Kolter. [doi]
- Self-supervised Visual Reinforcement Learning with Object-centric RepresentationsAndrii Zadaianchuk, Maximilian Seitzer, Georg Martius. [doi]
- A Temporal Kernel Approach for Deep Learning with Continuous-time InformationDa Xu, Chuanwei Ruan, Evren Körpeoglu, Sushant Kumar, Kannan Achan. [doi]
- Set Prediction without Imposing Structure as Conditional Density EstimationDavid W. Zhang, Gertjan J. Burghouts, Cees G. M. Snoek. [doi]
- Behavioral Cloning from Noisy DemonstrationsFumihiro Sasaki, Ryota Yamashina. [doi]
- Long Range Arena : A Benchmark for Efficient TransformersYi Tay, Mostafa Dehghani 0001, Samira Abnar, Yikang Shen, Dara Bahri, Philip Pham, Jinfeng Rao, Liu Yang, Sebastian Ruder, Donald Metzler. [doi]
- Influence Functions in Deep Learning Are FragileSamyadeep Basu, Phillip Pope, Soheil Feizi. [doi]
- Neurally Augmented ALISTAFreya Behrens, Jonathan Sauder, Peter Jung. [doi]
- Representation Learning for Sequence Data with Deep Autoencoding Predictive ComponentsJunwen Bai, Weiran Wang, Yingbo Zhou, Caiming Xiong. [doi]
- Neural gradients are near-lognormal: improved quantized and sparse trainingBrian Chmiel, Liad Ben-Uri, Moran Shkolnik, Elad Hoffer, Ron Banner, Daniel Soudry. [doi]
- Incremental few-shot learning via vector quantization in deep embedded spaceKuilin Chen, Chi-Guhn Lee. [doi]
- VA-RED2: Video Adaptive Redundancy ReductionBowen Pan, Rameswar Panda, Camilo Luciano Fosco, Chung-Ching Lin, Alex J. Andonian, Yue Meng, Kate Saenko, Aude Oliva, Rogério Feris. [doi]
- Towards Robust Neural Networks via Close-loop ControlZhuotong Chen, Qianxiao Li, Zheng Zhang. [doi]
- Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable LearningElan Sopher Markowitz, Keshav Balasubramanian, Mehrnoosh Mirtaheri, Sami Abu-El-Haija, Bryan Perozzi, Greg Ver Steeg, Aram Galstyan. [doi]
- On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-LearningRen Wang 0008, Kaidi Xu, Sijia Liu 0001, Pin-Yu Chen, Tsui-Wei Weng, Chuang Gan, Meng Wang. [doi]
- Generating Furry Cars: Disentangling Object Shape and Appearance across Multiple DomainsUtkarsh Ojha, Krishna Kumar Singh, Yong Jae Lee. [doi]
- HyperDynamics: Meta-Learning Object and Agent Dynamics with HypernetworksZhou Xian, Shamit Lal, Hsiao-Yu Tung, Emmanouil Antonios Platanios, Katerina Fragkiadaki. [doi]
- Revisiting Locally Supervised Learning: an Alternative to End-to-end TrainingYulin Wang, Zanlin Ni, Shiji Song, Le Yang, Gao Huang. [doi]
- Evaluation of Neural Architectures trained with square Loss vs Cross-Entropy in Classification TasksLike Hui, Mikhail Belkin. [doi]
- Predicting Infectiousness for Proactive Contact TracingYoshua Bengio, Prateek Gupta, Tegan Maharaj, Nasim Rahaman, Martin Weiss, Tristan Deleu, Eilif Benjamin Müller, Meng Qu, Victor Schmidt, Pierre-Luc St-Charles, Hannah Alsdurf, Olexa Bilaniuk, David Buckeridge, Gaétan Marceau-Caron, Pierre Luc Carrier, Joumana Ghosn, Satya Ortiz-Gagne, Christopher J. Pal, Irina Rish, Bernhard Schölkopf, Abhinav Sharma, Jian Tang, Andrew Williams. [doi]
- SOLAR: Sparse Orthogonal Learned and Random EmbeddingsTharun Medini, Beidi Chen, Anshumali Shrivastava. [doi]
- A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to AttentionGrégoire Mialon, Dexiong Chen, Alexandre d'Aspremont, Julien Mairal. [doi]
- Early Stopping in Deep Networks: Double Descent and How to Eliminate itReinhard Heckel, Fatih Furkan Yilmaz. [doi]
- An Unsupervised Deep Learning Approach for Real-World Image DenoisingDihan Zheng, Sia Huat Tan, Xiaowen Zhang, Zuoqiang Shi, Kaisheng Ma, Chenglong Bao. [doi]
- AdaFuse: Adaptive Temporal Fusion Network for Efficient Action RecognitionYue Meng, Rameswar Panda, Chung-Ching Lin, Prasanna Sattigeri, Leonid Karlinsky, Kate Saenko, Aude Oliva, Rogério Feris. [doi]
- The Traveling Observer Model: Multi-task Learning Through Spatial Variable EmbeddingsElliot Meyerson, Risto Miikkulainen. [doi]
- Empirical or Invariant Risk Minimization? A Sample Complexity PerspectiveKartik Ahuja, Jun Wang, Amit Dhurandhar, Karthikeyan Shanmugam, Kush R. Varshney. [doi]
- Learning from Protein Structure with Geometric Vector PerceptronsBowen Jing, Stephan Eismann, Patricia Suriana, Raphael John Lamarre Townshend, Ron O. Dror. [doi]
- Categorical Normalizing Flows via Continuous TransformationsPhillip Lippe, Efstratios Gavves. [doi]
- Deep Networks and the Multiple Manifold ProblemSam Buchanan, Dar Gilboa, John Wright 0001. [doi]
- Graph Convolution with Low-rank Learnable Local FiltersXiuyuan Cheng, Zichen Miao, Qiang Qiu. [doi]
- Learning N: M Fine-grained Structured Sparse Neural Networks From ScratchAojun Zhou, Yukun Ma, Junnan Zhu, Jianbo Liu, Zhijie Zhang, Kun Yuan, Wenxiu Sun, Hongsheng Li. [doi]
- Provable Rich Observation Reinforcement Learning with Combinatorial Latent StatesDipendra Misra, Qinghua Liu, Chi Jin, John Langford 0001. [doi]
- Improving Zero-Shot Voice Style Transfer via Disentangled Representation LearningSiyang Yuan, Pengyu Cheng, Ruiyi Zhang, Weituo Hao, Zhe Gan, Lawrence Carin. [doi]
- ALFWorld: Aligning Text and Embodied Environments for Interactive LearningMohit Shridhar, Xingdi Yuan, Marc-Alexandre Côté, Yonatan Bisk, Adam Trischler, Matthew J. Hausknecht. [doi]
- Continuous Wasserstein-2 Barycenter Estimation without Minimax OptimizationAlexander Korotin, Lingxiao Li, Justin Solomon 0001, Evgeny Burnaev. [doi]
- PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable PhysicsZhiao Huang, Yuanming Hu, Tao Du, Siyuan Zhou, Hao Su 0001, Joshua B. Tenenbaum, Chuang Gan. [doi]
- Saliency is a Possible Red Herring When Diagnosing Poor GeneralizationJoseph D. Viviano, Becks Simpson, Francis Dutil, Yoshua Bengio, Joseph Paul Cohen. [doi]
- Measuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, Jacob Steinhardt. [doi]
- Regularization Matters in Policy Optimization - An Empirical Study on Continuous ControlZhuang Liu 0003, Xuanlin Li, Bingyi Kang, Trevor Darrell. [doi]
- Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated EnvironmentsDaochen Zha, Wenye Ma, Lei Yuan, Xia Hu, Ji Liu. [doi]
- QPLEX: Duplex Dueling Multi-Agent Q-LearningJianhao Wang, Zhizhou Ren, Terry Liu, Yang Yu, Chongjie Zhang. [doi]
- Learning A Minimax Optimizer: A Pilot StudyJiayi Shen, Xiaohan Chen, Howard Heaton, Tianlong Chen, Jialin Liu 0003, Wotao Yin, Zhangyang Wang. [doi]
- Multi-resolution modeling of a discrete stochastic process identifies causes of cancerAdam Uri Yaari, Maxwell Sherman, Oliver Clarke Priebe, Po-Ru Loh, Boris Katz, Andrei Barbu, Bonnie Berger. [doi]
- Hierarchical Reinforcement Learning by Discovering Intrinsic OptionsJesse Zhang, Haonan Yu, Wei Xu. [doi]
- Global optimality of softmax policy gradient with single hidden layer neural networks in the mean-field regimeAndrea Agazzi, Jianfeng Lu. [doi]
- Combining Physics and Machine Learning for Network Flow EstimationArlei Lopes da Silva, Furkan Kocayusufoglu, Saber Jafarpour, Francesco Bullo, Ananthram Swami, Ambuj K. Singh. [doi]
- Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHSLin Chen, Sheng Xu. [doi]
- Sliced Kernelized Stein DiscrepancyWenbo Gong 0001, Yingzhen Li, José Miguel Hernández-Lobato. [doi]
- Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive LearningTsung-Wei Ke, Jyh-Jing Hwang, Stella Yu. [doi]
- The Intrinsic Dimension of Images and Its Impact on LearningPhillip Pope, Chen Zhu, Ahmed Abdelkader, Micah Goldblum, Tom Goldstein. [doi]
- Efficient Continual Learning with Modular Networks and Task-Driven PriorsTom Veniat, Ludovic Denoyer, Marc'Aurelio Ranzato. [doi]
- Learning Generalizable Visual Representations via Interactive GameplayLuca Weihs, Aniruddha Kembhavi, Kiana Ehsani, Sarah M. Pratt, Winson Han, Alvaro Herrasti, Eric Kolve, Dustin Schwenk, Roozbeh Mottaghi, Ali Farhadi. [doi]
- Property Controllable Variational Autoencoder via Invertible Mutual DependenceXiaojie Guo, Yuanqi Du, Liang Zhao. [doi]
- Winning the L2RPN Challenge: Power Grid Management via Semi-Markov Afterstate Actor-CriticDeunsol Yoon, Sunghoon Hong, Byung-Jun Lee 0001, Kee-Eung Kim. [doi]
- Variational Intrinsic Control RevisitedTaehwan Kwon. [doi]
- MELR: Meta-Learning via Modeling Episode-Level Relationships for Few-Shot LearningNanyi Fei, Zhiwu Lu, Tao Xiang, Songfang Huang. [doi]
- Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient EstimatorMax B. Paulus, Chris J. Maddison, Andreas Krause 0001. [doi]
- Open Question Answering over Tables and TextWenhu Chen, Ming-Wei Chang, Eva Schlinger, William Yang Wang, William W. Cohen. [doi]
- Debiasing Concept-based Explanations with Causal AnalysisMohammad Taha Bahadori, David Heckerman. [doi]
- SMiRL: Surprise Minimizing Reinforcement Learning in Unstable EnvironmentsGlen Berseth, Daniel Geng, Coline Manon Devin, Nicholas Rhinehart, Chelsea Finn, Dinesh Jayaraman, Sergey Levine. [doi]
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano Ermon. [doi]
- Semi-supervised Keypoint LocalizationOlga Moskvyak, Frédéric Maire, Feras Dayoub, Mahsa Baktashmotlagh. [doi]
- Learning "What-if" Explanations for Sequential Decision-MakingIoana Bica, Daniel Jarrett, Alihan Hüyük, Mihaela van der Schaar. [doi]
- Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence LearningXuebo Liu 0002, Longyue Wang, Derek F. Wong, Liang Ding, Lidia S. Chao, Zhaopeng Tu. [doi]
- NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose EstimationAngtian Wang, Adam Kortylewski, Alan L. Yuille. [doi]
- SSD: A Unified Framework for Self-Supervised Outlier DetectionVikash Sehwag, Mung Chiang, Prateek Mittal. [doi]
- Adversarially-Trained Deep Nets Transfer Better: Illustration on Image ClassificationFrancisco Utrera, Evan Kravitz, N. Benjamin Erichson, Rajiv Khanna, Michael W. Mahoney. [doi]
- Explainable Deep One-Class ClassificationPhilipp Liznerski, Lukas Ruff, Robert A. Vandermeulen, Billy Joe Franks, Marius Kloft, Klaus-Robert Müller. [doi]
- Are Neural Rankers still Outperformed by Gradient Boosted Decision Trees?Zhen Qin 0002, Le Yan, Honglei Zhuang, Yi Tay, Rama Kumar Pasumarthi, Xuanhui Wang, Michael Bendersky, Marc Najork. [doi]
- DiffWave: A Versatile Diffusion Model for Audio SynthesisZhifeng Kong, Wei Ping, Jiaji Huang, Kexin Zhao, Bryan Catanzaro. [doi]
- Net-DNF: Effective Deep Modeling of Tabular DataLiran Katzir 0001, Gal Elidan, Ran El-Yaniv. [doi]
- CT-Net: Channel Tensorization Network for Video ClassificationKunchang Li, Xianhang Li, Yali Wang, Jun Wang, Yu Qiao. [doi]
- Entropic gradient descent algorithms and wide flat minimaFabrizio Pittorino, Carlo Lucibello, Christoph Feinauer, Gabriele Perugini, Carlo Baldassi, Elizaveta Demyanenko, Riccardo Zecchina. [doi]
- Reset-Free Lifelong Learning with Skill-Space PlanningKevin Lu, Aditya Grover, Pieter Abbeel, Igor Mordatch. [doi]
- Fully Unsupervised Diversity Denoising with Convolutional Variational AutoencodersMangal Prakash, Alexander Krull, Florian Jug. [doi]
- Neural Delay Differential EquationsQunxi Zhu, Yao Guo, Wei Lin. [doi]
- Combining Label Propagation and Simple Models out-performs Graph Neural NetworksQian Huang, Horace He, Abhay Singh, Ser-Nam Lim, Austin R. Benson. [doi]
- Universal approximation power of deep residual neural networks via nonlinear control theoryPaulo Tabuada, Bahman Gharesifard. [doi]
- Dataset Inference: Ownership Resolution in Machine LearningPratyush Maini, Mohammad Yaghini, Nicolas Papernot. [doi]
- Intrinsic-Extrinsic Convolution and Pooling for Learning on 3D Protein StructuresPedro Hermosilla, Marco Schäfer, Matej Lang, Gloria Fackelmann, Pere-Pau Vázquez, Barbora Kozlíková, Michael Krone, Tobias Ritschel 0001, Timo Ropinski. [doi]
- Go with the flow: Adaptive control for Neural ODEsMathieu Chalvidal, Matthew Ricci, Rufin VanRullen, Thomas Serre. [doi]
- Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning DynamicsDaniel Kunin, Javier Sagastuy-Breña, Surya Ganguli, Daniel L. Yamins, Hidenori Tanaka. [doi]
- SEED: Self-supervised Distillation For Visual RepresentationZhiyuan Fang, Jianfeng Wang, Lijuan Wang, Lei Zhang, Yezhou Yang, Zicheng Liu 0001. [doi]
- Neural networks with late-phase weightsJohannes von Oswald, Seijin Kobayashi, João Sacramento, Alexander Meulemans, Christian Henning, Benjamin F. Grewe. [doi]
- Partitioned Learned Bloom FiltersKapil Vaidya, Eric Knorr, Michael Mitzenmacher, Tim Kraska. [doi]
- Impact of Representation Learning in Linear BanditsJiaqi Yang, Wei Hu, Jason D. Lee, Simon Shaolei Du. [doi]
- Rethinking the Role of Gradient-based Attribution Methods for Model InterpretabilitySuraj Srinivas, François Fleuret. [doi]
- Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphsPim de Haan, Maurice Weiler, Taco Cohen, Max Welling. [doi]
- Local Search Algorithms for Rank-Constrained Convex OptimizationKyriakos Axiotis, Maxim Sviridenko. [doi]
- Statistical inference for individual fairnessSubha Maity, Songkai Xue, Mikhail Yurochkin, Yuekai Sun. [doi]
- Beyond Categorical Label Representations for Image ClassificationBoyuan Chen, Yu Li, Sunand Raghupathi, Hod Lipson. [doi]
- Improved Autoregressive Modeling with Distribution SmoothingChenlin Meng, Jiaming Song, Yang Song 0011, Shengjia Zhao, Stefano Ermon. [doi]
- Learning to Represent Action Values as a Hypergraph on the Action VerticesArash Tavakoli, Mehdi Fatemi, Petar Kormushev. [doi]
- Learning and Evaluating Representations for Deep One-Class ClassificationKihyuk Sohn, Chun-Liang Li, Jinsung Yoon, Minho Jin, Tomas Pfister. [doi]
- On Statistical Bias In Active Learning: How and When to Fix ItSebastian Farquhar, Yarin Gal, Tom Rainforth. [doi]
- Computational Separation Between Convolutional and Fully-Connected NetworksEran Malach, Shai Shalev-Shwartz. [doi]
- WaveGrad: Estimating Gradients for Waveform GenerationNanxin Chen, Yu Zhang, Heiga Zen, Ron J. Weiss, Mohammad Norouzi 0002, William Chan. [doi]
- A Mathematical Exploration of Why Language Models Help Solve Downstream TasksNikunj Saunshi, Sadhika Malladi, Sanjeev Arora. [doi]
- Self-supervised Adversarial Robustness for the Low-label, High-data RegimeSven Gowal, Po-Sen Huang, Aäron Van Den Oord, Timothy Mann, Pushmeet Kohli. [doi]
- Efficient Certified Defenses Against Patch Attacks on Image ClassifiersJan Hendrik Metzen, Maksym Yatsura. [doi]
- Scaling Symbolic Methods using Gradients for Neural Model ExplanationSubham Sekhar Sahoo, Subhashini Venugopalan, Li Li 0060, Rishabh Singh, Patrick Riley 0001. [doi]
- Meta-Learning of Structured Task Distributions in Humans and MachinesSreejan Kumar, Ishita Dasgupta, Jonathan D. Cohen 0003, Nathaniel D. Daw, Thomas L. Griffiths. [doi]
- Kanerva++: Extending the Kanerva Machine With Differentiable, Locally Block Allocated Latent MemoryJason Ramapuram, Yan Wu, Alexandros Kalousis. [doi]
- Prediction and generalisation over directed actions by grid cellsChangmin Yu, Timothy Behrens, Neil Burgess. [doi]
- Do not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private LearningDa Yu, Huishuai Zhang, Wei Chen 0034, Tie-Yan Liu. [doi]
- TropEx: An Algorithm for Extracting Linear Terms in Deep Neural NetworksMartin Trimmel, Henning Petzka, Cristian Sminchisescu. [doi]
- A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network InferenceSanghyun Hong, Yigitcan Kaya, Ionut-Vlad Modoranu, Tudor Dumitras. [doi]
- Long Live the Lottery: The Existence of Winning Tickets in Lifelong LearningTianlong Chen, Zhenyu Zhang, Sijia Liu 0001, Shiyu Chang, Zhangyang Wang. [doi]
- PMI-Masking: Principled masking of correlated spansYoav Levine, Barak Lenz, Opher Lieber, Omri Abend, Kevin Leyton-Brown, Moshe Tennenholtz, Yoav Shoham. [doi]
- Neural ODE ProcessesAlexander Norcliffe, Cristian Bodnar, Ben Day, Jacob Moss, Pietro Liò. [doi]
- Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust ExplorationJaekyeom Kim, Minjung Kim, Dongyeon Woo, Gunhee Kim. [doi]
- Stabilized Medical Image AttacksGege Qi, Lijun Gong, Yibing Song, Kai Ma 0002, Yefeng Zheng. [doi]
- Continual learning in recurrent neural networksBenjamin Ehret, Christian Henning, Maria R. Cervera, Alexander Meulemans, Johannes von Oswald, Benjamin F. Grewe. [doi]
- Adaptive Procedural Task Generation for Hard-Exploration ProblemsKuan Fang, Yuke Zhu, Silvio Savarese, Fei-Fei Li 0001. [doi]
- Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial ExamplesZiang Yan, Yiwen Guo, Jian Liang, Changshui Zhang. [doi]
- Pre-training Text-to-Text Transformers for Concept-centric Common SenseWangchunshu Zhou, Dong-Ho Lee, Ravi Kiran Selvam, Seyeon Lee, Xiang Ren 0001. [doi]
- Molecule Optimization by Explainable EvolutionBinghong Chen, Tianzhe Wang, Chengtao Li, Hanjun Dai, Le Song. [doi]
- Fast convergence of stochastic subgradient method under interpolationHuang Fang, Zhenan Fan, Michael P. Friedlander. [doi]
- Remembering for the Right Reasons: Explanations Reduce Catastrophic ForgettingSayna Ebrahimi, Suzanne Petryk, Akash Gokul, William Gan, Joseph E. Gonzalez, Marcus Rohrbach, Trevor Darrell. [doi]
- Learning with AMIGo: Adversarially Motivated Intrinsic GoalsAndres Campero, Roberta Raileanu, Heinrich Küttler, Joshua B. Tenenbaum, Tim Rocktäschel, Edward Grefenstette. [doi]
- Autoregressive Dynamics Models for Offline Policy Evaluation and OptimizationMichael R. Zhang, Thomas Paine, Ofir Nachum, Cosmin Paduraru, George Tucker, Ziyu Wang 0001, Mohammad Norouzi 0002. [doi]
- Sample-Efficient Automated Deep Reinforcement LearningJörg K. H. Franke, Gregor Köhler, André Biedenkapp, Frank Hutter. [doi]
- Conditional Negative Sampling for Contrastive Learning of Visual RepresentationsMike Wu, Milan Mosse, Chengxu Zhuang, Daniel Yamins, Noah D. Goodman. [doi]
- MARS: Markov Molecular Sampling for Multi-objective Drug DiscoveryYutong Xie, Chence Shi, Hao Zhou, Yuwei Yang, Weinan Zhang 0001, Yong Yu 0001, Lei Li 0005. [doi]
- Combining Ensembles and Data Augmentation Can Harm Your CalibrationYeming Wen, Ghassen Jerfel, Rafael Muller, Michael W. Dusenberry, Jasper Snoek, Balaji Lakshminarayanan, Dustin Tran. [doi]
- Temporally-Extended ε-Greedy ExplorationWill Dabney, Georg Ostrovski, André Barreto. [doi]
- BUSTLE: Bottom-Up Program Synthesis Through Learning-Guided ExplorationAugustus Odena, Kensen Shi, David Bieber, Rishabh Singh, Charles Sutton, Hanjun Dai. [doi]
- Adapting to Reward Progressivity via Spectral Reinforcement LearningMichael Dann, John Thangarajah. [doi]
- Analyzing the Expressive Power of Graph Neural Networks in a Spectral PerspectiveMuhammet Balcilar, Guillaume Renton, Pierre Héroux, Benoit Gaüzère, Sébastien Adam, Paul Honeine. [doi]
- Scalable Transfer Learning with Expert ModelsJoan Puigcerver, Carlos Riquelme Ruiz, Basil Mustafa, Cédric Renggli, André Susano Pinto, Sylvain Gelly, Daniel Keysers, Neil Houlsby. [doi]
- UMEC: Unified model and embedding compression for efficient recommendation systemsJiayi Shen, Haotao Wang, Shupeng Gui, Jianchao Tan, Zhangyang Wang, Ji Liu. [doi]
- FairFil: Contrastive Neural Debiasing Method for Pretrained Text EncodersPengyu Cheng, Weituo Hao, Siyang Yuan, Shijing Si, Lawrence Carin. [doi]
- Mastering Atari with Discrete World ModelsDanijar Hafner, Timothy P. Lillicrap, Mohammad Norouzi 0002, Jimmy Ba. [doi]
- MoVie: Revisiting Modulated Convolutions for Visual Counting and BeyondDuy-Kien Nguyen, Vedanuj Goswami, Xinlei Chen. [doi]
- Extracting Strong Policies for Robotics Tasks from Zero-Order Trajectory OptimizersCristina Pinneri, Shambhuraj Sawant, Sebastian Blaes, Georg Martius. [doi]
- Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen SoundsEfthymios Tzinis, Scott Wisdom, Aren Jansen, Shawn Hershey, Tal Remez, Dan Ellis, John R. Hershey. [doi]
- Uncertainty-aware Active Learning for Optimal Bayesian ClassifierGuang Zhao, Edward R. Dougherty, Byung-Jun Yoon, Francis J. Alexander, Xiaoning Qian. [doi]
- Discovering Diverse Multi-Agent Strategic Behavior via Reward RandomizationZhenggang Tang, Chao Yu, Boyuan Chen, Huazhe Xu, Xiaolong Wang 0004, Fei Fang, Simon Shaolei Du, Yu Wang, Yi Wu. [doi]
- Creative Sketch GenerationSongwei Ge, Vedanuj Goswami, Larry Zitnick, Devi Parikh. [doi]
- Wasserstein Embedding for Graph LearningSoheil Kolouri, Navid Naderializadeh, Gustavo K. Rohde, Heiko Hoffmann. [doi]
- Learning Associative Inference Using Fast Weight MemoryImanol Schlag, Tsendsuren Munkhdalai, Jürgen Schmidhuber. [doi]
- Negative Data AugmentationAbhishek Sinha, Kumar Ayush, Jiaming Song, Burak Uzkent, Hongxia Jin, Stefano Ermon. [doi]
- Explainable Subgraph Reasoning for Forecasting on Temporal Knowledge GraphsZhen Han, Peng Chen, Yunpu Ma, Volker Tresp. [doi]
- Hopfield Networks is All You NeedHubert Ramsauer, Bernhard Schäfl, Johannes Lehner, Philipp Seidl, Michael Widrich, Lukas Gruber, Markus Holzleitner, Thomas Adler, David P. Kreil, Michael K. Kopp 0001, Günter Klambauer, Johannes Brandstetter, Sepp Hochreiter. [doi]
- Learning from others' mistakes: Avoiding dataset biases without modeling themVictor Sanh, Thomas Wolf 0008, Yonatan Belinkov, Alexander M. Rush. [doi]
- Long-tail learning via logit adjustmentAditya Krishna Menon, Sadeep Jayasumana, Ankit Singh Rawat, Himanshu Jain, Andreas Veit, Sanjiv Kumar. [doi]
- Hyperbolic Neural Networks++Ryohei Shimizu, Yusuke Mukuta, Tatsuya Harada. [doi]
- Primal Wasserstein Imitation LearningRobert Dadashi, Léonard Hussenot, Matthieu Geist, Olivier Pietquin. [doi]
- On the Origin of Implicit Regularization in Stochastic Gradient DescentSamuel L. Smith, Benoit Dherin, David G. T. Barrett, Soham De. [doi]
- Memory Optimization for Deep NetworksAashaka Shah, Chao-Yuan Wu, Jayashree Mohan, Vijay Chidambaram, Philipp Krähenbühl. [doi]
- Symmetry-Aware Actor-Critic for 3D Molecular DesignGregor N. C. Simm, Robert Pinsler, Gábor Csányi, José Miguel Hernández-Lobato. [doi]
- Single-Timescale Actor-Critic Provably Finds Globally Optimal PolicyZuyue Fu, Zhuoran Yang, Zhaoran Wang. [doi]
- Sparse encoding for more-interpretable feature-selecting representations in probabilistic matrix factorizationJoshua C. Chang, Patrick Fletcher, Jungmin Han, Ted L. Chang, Shashaank Vattikuti, Bart Desmet, Ayah Zirikly, Carson C. Chow. [doi]
- Task-Agnostic Morphology EvolutionDonald Joseph Hejna III, Pieter Abbeel, Lerrel Pinto. [doi]
- SkipW: Resource Adaptable RNN with Strict Upper Computational LimitTsiry Mayet, Anne Lambert, Pascal LeGuyadec, Françoise Le Bolzer, François Schnitzler. [doi]
- Colorization TransformerManoj Kumar, Dirk Weissenborn, Nal Kalchbrenner. [doi]
- Discovering a set of policies for the worst case rewardTom Zahavy, André Barreto, Daniel J. Mankowitz, Shaobo Hou, Brendan O'Donoghue, Iurii Kemaev, Satinder Singh. [doi]
- Estimating and Evaluating Regression Predictive Uncertainty in Deep Object DetectorsAli Harakeh, Steven L. Waslander. [doi]
- Loss Function Discovery for Object Detection via Convergence-Simulation Driven SearchPeidong Liu, Gengwei Zhang, Bochao Wang, Hang Xu, Xiaodan Liang, Yong Jiang, Zhenguo Li. [doi]
- PolarNet: Learning to Optimize Polar Keypoints for Keypoint Based Object DetectionXiongwei Wu, Doyen Sahoo, Steven C. H. Hoi. [doi]
- Convex Regularization behind Neural ReconstructionArda Sahiner, Morteza Mardani, Batu Ozturkler, Mert Pilanci, John M. Pauly. [doi]
- Filtered Inner Product Projection for Crosslingual Embedding AlignmentVin Sachidananda, Ziyi Yang, Chenguang Zhu. [doi]
- Recurrent Independent MechanismsAnirudh Goyal, Alex Lamb, Jordan Hoffmann, Shagun Sodhani, Sergey Levine, Yoshua Bengio, Bernhard Schölkopf. [doi]
- Rethinking Attention with PerformersKrzysztof Marcin Choromanski, Valerii Likhosherstov, David Dohan, Xingyou Song, Andreea Gane, Tamás Sarlós, Peter Hawkins, Jared Quincy Davis, Afroz Mohiuddin, Lukasz Kaiser, David Benjamin Belanger, Lucy J. Colwell, Adrian Weller. [doi]
- CopulaGNN: Towards Integrating Representational and Correlational Roles of Graphs in Graph Neural NetworksJiaqi Ma 0001, Bo Chang, Xuefei Zhang, Qiaozhu Mei. [doi]
- Watch-And-Help: A Challenge for Social Perception and Human-AI CollaborationXavier Puig, Tianmin Shu, Shuang Li, Zilin Wang, Yuan-Hong Liao, Joshua B. Tenenbaum, Sanja Fidler, Antonio Torralba 0001. [doi]
- Multi-timescale Representation Learning in LSTM Language ModelsShivangi Mahto, Vy Ai Vo, Javier S. Turek, Alexander Huth. [doi]
- not-MIWAE: Deep Generative Modelling with Missing not at Random DataNiels Bruun Ipsen, Pierre-Alexandre Mattei, Jes Frellsen. [doi]
- PC2WF: 3D Wireframe Reconstruction from Raw Point CloudsYujia Liu, Stefano D'Aronco, Konrad Schindler, Jan Dirk Wegner. [doi]
- The inductive bias of ReLU networks on orthogonally separable dataMary Phuong, Christoph H. Lampert. [doi]
- Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from PixelsDenis Yarats, Ilya Kostrikov, Rob Fergus. [doi]
- Contrastive Divergence Learning is a Time Reversal Adversarial GameOmer Yair, Tomer Michaeli. [doi]
- The role of Disentanglement in GeneralisationMilton Llera Montero, Casimir JH Ludwig, Rui Ponte Costa, Gaurav Malhotra, Jeffrey Bowers. [doi]
- A Wigner-Eckart Theorem for Group Equivariant Convolution KernelsLeon Lang, Maurice Weiler. [doi]
- Learning Deep Features in Instrumental Variable RegressionLiyuan Xu, Yutian Chen, Siddarth Srinivasan, Nando de Freitas, Arnaud Doucet, Arthur Gretton. [doi]
- Self-supervised Representation Learning with Relative Predictive CodingYao-Hung Hubert Tsai, Martin Q. Ma, Muqiao Yang, Han Zhao 0002, Louis-Philippe Morency, Ruslan Salakhutdinov. [doi]
- INT: An Inequality Benchmark for Evaluating Generalization in Theorem ProvingYuhuai Wu, Albert Jiang, Jimmy Ba, Roger Baker Grosse. [doi]
- On Self-Supervised Image Representations for GAN EvaluationStanislav Morozov, Andrey Voynov, Artem Babenko. [doi]
- One Network Fits All? Modular versus Monolithic Task Formulations in Neural NetworksAtish Agarwala, Abhimanyu Das, Brendan Juba, Rina Panigrahy, Vatsal Sharan, Xin Wang, Qiuyi Zhang. [doi]
- Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methodsTaiji Suzuki, Shunta Akiyama. [doi]
- On the role of planning in model-based deep reinforcement learningJessica B. Hamrick, Abram L. Friesen, Feryal Behbahani, Arthur Guez, Fabio Viola, Sims Witherspoon, Thomas Anthony, Lars Holger Buesing, Petar Velickovic, Theophane Weber. [doi]
- Supervised Contrastive Learning for Pre-trained Language Model Fine-tuningBeliz Gunel, Jingfei Du, Alexis Conneau, Veselin Stoyanov. [doi]
- Extreme Memorization via Scale of InitializationHarsh Mehta, Ashok Cutkosky, Behnam Neyshabur. [doi]
- Representation Balancing Offline Model-based Reinforcement LearningByung-Jun Lee 0001, Jongmin Lee 0004, Kee-Eung Kim. [doi]
- A Universal Representation Transformer Layer for Few-Shot Image ClassificationLu Liu, William L. Hamilton, Guodong Long, Jing Jiang, Hugo Larochelle. [doi]
- MultiModalQA: complex question answering over text, tables and imagesAlon Talmor, Ori Yoran, Amnon Catav, Dan Lahav, Yizhong Wang, Akari Asai, Gabriel Ilharco, Hannaneh Hajishirzi, Jonathan Berant. [doi]
- HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous ClientsEnmao Diao, Jie Ding 0002, Vahid Tarokh. [doi]
- Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPUPatrick Kidger, Terry J. Lyons. [doi]
- ResNet After All: Neural ODEs and Their Numerical SolutionKatharina Ott, Prateek Katiyar, Philipp Hennig, Michael Tiemann. [doi]
- Probabilistic Numeric Convolutional Neural NetworksMarc Anton Finzi, Roberto Bondesan, Max Welling. [doi]
- Tradeoffs in Data Augmentation: An Empirical StudyRaphael Gontijo Lopes, Sylvia J. Smullin, Ekin Dogus Cubuk, Ethan Dyer. [doi]
- Repurposing Pretrained Models for Robust Out-of-domain Few-Shot LearningNamYeong Kwon, Hwidong Na, Gabriel Huang, Simon Lacoste-Julien. [doi]
- High-Capacity Expert Binary NetworksAdrian Bulat, Brais Martínez, Georgios Tzimiropoulos. [doi]
- Benchmarks for Deep Off-Policy EvaluationJustin Fu, Mohammad Norouzi 0002, Ofir Nachum, George Tucker, Ziyu Wang 0001, Alexander Novikov 0001, Mengjiao Yang, Michael R. Zhang, Yutian Chen, Aviral Kumar, Cosmin Paduraru, Sergey Levine, Thomas Paine. [doi]
- Rapid Task-Solving in Novel EnvironmentsSamuel Ritter, Ryan Faulkner, Laurent Sartran, Adam Santoro, Matthew Botvinick, David Raposo. [doi]
- Training with Quantization Noise for Extreme Model CompressionPierre Stock, Angela Fan, Benjamin Graham, Edouard Grave, Rémi Gribonval, Hervé Jégou, Armand Joulin. [doi]
- Protecting DNNs from Theft using an Ensemble of Diverse ModelsSanjay Kariyappa, Atul Prakash 0001, Moinuddin K. Qureshi. [doi]
- Self-training For Few-shot Transfer Across Extreme Task DifferencesCheng Perng Phoo, Bharath Hariharan. [doi]
- MoPro: Webly Supervised Learning with Momentum PrototypesJunnan Li 0001, Caiming Xiong, Steven C. H. Hoi. [doi]
- PSTNet: Point Spatio-Temporal Convolution on Point Cloud SequencesHehe Fan, Xin Yu, Yuhang Ding, Yi Yang, Mohan S. Kankanhalli. [doi]
- Fidelity-based Deep Adiabatic SchedulingEli Ovits, Lior Wolf. [doi]
- Generalization bounds via distillationDaniel Hsu 0001, Ziwei Ji, Matus Telgarsky, Lan Wang. [doi]
- Mixed-Features Vectors and Subspace SplittingAlejandro Pimentel-Alarcón, Daniel L. Pimentel-Alarcón. [doi]
- Bayesian Context Aggregation for Neural ProcessesMichael Volpp, Fabian Flürenbrock, Lukas Großberger, Christian Daniel, Gerhard Neumann. [doi]
- Efficient Transformers in Reinforcement Learning using Actor-Learner DistillationEmilio Parisotto, Russ R. Salakhutdinov. [doi]
- GAN "Steerability" without optimizationNurit Spingarn, Ron Banner, Tomer Michaeli. [doi]
- A unifying view on implicit bias in training linear neural networksChulhee Yun, Shankar Krishnan, Hossein Mobahi. [doi]
- FairBatch: Batch Selection for Model FairnessYuji Roh, Kangwook Lee 0001, Steven Euijong Whang, Changho Suh. [doi]
- Multi-Level Local SGD: Distributed SGD for Heterogeneous Hierarchical NetworksTimothy Castiglia, Anirban Das, Stacy Patterson. [doi]
- A Design Space Study for LISTA and BeyondTianjian Meng, Xiaohan Chen, Yifan Jiang, Zhangyang Wang. [doi]
- Improving VAEs' Robustness to Adversarial AttackMatthew Willetts, Alexander Camuto, Tom Rainforth, Stephen J. Roberts, Christopher C. Holmes. [doi]
- gradSim: Differentiable simulation for system identification and visuomotor controlJ. Krishna Murthy, Miles Macklin, Florian Golemo, Vikram Voleti, Linda Petrini, Martin Weiss, Breandan Considine, Jérôme Parent-Lévesque, Kevin Xie, Kenny Erleben, Liam Paull, Florian Shkurti, Derek Nowrouzezahrai, Sanja Fidler. [doi]
- Systematic generalisation with group invariant predictionsFaruk Ahmed, Yoshua Bengio, Harm van Seijen, Aaron C. Courville. [doi]
- On Graph Neural Networks versus Graph-Augmented MLPsLei Chen 0062, Zhengdao Chen, Joan Bruna. [doi]
- On Learning Universal Representations Across LanguagesXiangpeng Wei, Rongxiang Weng, Yue Hu 0002, Luxi Xing, Heng Yu, Weihua Luo. [doi]
- Iterated learning for emergent systematicity in VQAAnkit Vani, Max Schwarzer, Yuchen Lu, Eeshan Dhekane, Aaron C. Courville. [doi]
- Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based ModelsMitch Hill, Jonathan Craig Mitchell, Song Chun Zhu. [doi]
- Learning to Deceive Knowledge Graph Augmented Models via Targeted PerturbationMrigank Raman, Aaron Chan, Siddhant Agarwal, PeiFeng Wang, Hansen Wang, SungChul Kim, Ryan A. Rossi, Handong Zhao, Nedim Lipka, Xiang Ren 0001. [doi]
- Grounded Language Learning Fast and SlowFelix Hill, Olivier Tieleman, Tamara von Glehn, Nathaniel Wong, Hamza Merzic, Stephen Clark. [doi]
- Rethinking Architecture Selection in Differentiable NASRuochen Wang, Minhao Cheng, Xiangning Chen, Xiaocheng Tang, Cho-Jui Hsieh. [doi]
- Distance-Based Regularisation of Deep Networks for Fine-TuningHenry Gouk, Timothy M. Hospedales, Massimiliano Pontil. [doi]
- Fast Geometric Projections for Local Robustness CertificationAymeric Fromherz, Klas Leino, Matt Fredrikson, Bryan Parno, Corina S. Pasareanu. [doi]
- SCoRe: Pre-Training for Context Representation in Conversational Semantic ParsingTao Yu 0009, Rui Zhang, Alex Polozov, Christopher Meek, Ahmed Hassan Awadallah. [doi]
- BiPointNet: Binary Neural Network for Point CloudsHaotong Qin, Zhongang Cai, Mingyuan Zhang, Yifu Ding, Haiyu Zhao, Shuai Yi, Xianglong Liu, Hao Su. [doi]
- Probing BERT in Hyperbolic SpacesBoli Chen, Yao Fu, Guangwei Xu, Pengjun Xie, Chuanqi Tan, Mosha Chen, Liping Jing. [doi]
- On the Impossibility of Global Convergence in Multi-Loss OptimizationAlistair Letcher. [doi]
- What they do when in doubt: a study of inductive biases in seq2seq learnersEugene Kharitonov, Rahma Chaabouni. [doi]
- A Good Image Generator Is What You Need for High-Resolution Video SynthesisYu Tian, Jian Ren, Menglei Chai, Kyle Olszewski, Xi Peng 0005, Dimitris N. Metaxas, Sergey Tulyakov. [doi]
- A Better Alternative to Error Feedback for Communication-Efficient Distributed LearningSamuel Horváth, Peter Richtárik. [doi]
- Boost then Convolve: Gradient Boosting Meets Graph Neural NetworksSergei Ivanov 0004, Liudmila Prokhorenkova. [doi]
- Parameter Efficient Multimodal Transformers for Video Representation LearningSangho Lee, Youngjae Yu, Gunhee Kim, Thomas Breuel, Jan Kautz, Yale Song. [doi]
- Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank LearningZhiyuan Li 0005, Yuping Luo, Kaifeng Lyu. [doi]
- Differentiable Trust Region Layers for Deep Reinforcement LearningFabian Otto, Philipp Becker, Ngo Anh Vien, Hanna Carolin Maria Ziesche, Gerhard Neumann. [doi]
- Co-Mixup: Saliency Guided Joint Mixup with Supermodular DiversityJang-Hyun Kim, Wonho Choo, Hosan Jeong, Hyun Oh Song. [doi]
- Off-Dynamics Reinforcement Learning: Training for Transfer with Domain ClassifiersBenjamin Eysenbach, Shreyas Chaudhari, Swapnil Asawa, Sergey Levine, Ruslan Salakhutdinov. [doi]
- Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint LearningWonyong Jeong, Jaehong Yoon, Eunho Yang, Sung Ju Hwang. [doi]
- Parrot: Data-Driven Behavioral Priors for Reinforcement LearningAvi Singh, Huihan Liu, Gaoyue Zhou, Albert Yu, Nicholas Rhinehart, Sergey Levine. [doi]
- Representation learning for improved interpretability and classification accuracy of clinical factors from EEGGarrett Honke, Irina Higgins, Nina Thigpen, Vladimir Miskovic, Katie Link, Sunny Duan, Pramod Gupta, Julia Klawohn, Greg Hajcak. [doi]
- Learning to Reach Goals via Iterated Supervised LearningDibya Ghosh, Abhishek Gupta 0004, Ashwin Reddy, Justin Fu, Coline Manon Devin, Benjamin Eysenbach, Sergey Levine. [doi]
- Identifying nonlinear dynamical systems with multiple time scales and long-range dependenciesDominik Schmidt, Georgia Koppe, Zahra Monfared, Max Beutelspacher, Daniel Durstewitz. [doi]
- Learning to Recombine and Resample Data For Compositional GeneralizationEkin Akyürek, Afra Feyza Akyürek, Jacob Andreas. [doi]
- Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing FlowsKashif Rasul, Abdul-Saboor Sheikh, Ingmar Schuster, Urs M. Bergmann, Roland Vollgraf. [doi]
- Retrieval-Augmented Generation for Code Summarization via Hybrid GNNShangqing Liu, Yu Chen, Xiaofei Xie, Jing Kai Siow, Yang Liu 0003. [doi]
- Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and DepthThao Nguyen, Maithra Raghu, Simon Kornblith. [doi]
- No MCMC for me: Amortized sampling for fast and stable training of energy-based modelsWill Sussman Grathwohl, Jacob Jin Kelly, Milad Hashemi, Mohammad Norouzi 0002, Kevin Swersky, David Duvenaud. [doi]
- Simple Augmentation Goes a Long Way: ADRL for DNN QuantizationLin Ning 0001, Guoyang Chen, Weifeng Zhang, Xipeng Shen. [doi]
- Transient Non-stationarity and Generalisation in Deep Reinforcement LearningMaximilian Igl, Gregory Farquhar, Jelena Luketina, Wendelin Boehmer, Shimon Whiteson. [doi]
- Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?Balázs Kégl, Gabriel Hurtado, Albert Thomas. [doi]
- HalentNet: Multimodal Trajectory Forecasting with Hallucinative IntentsDeyao Zhu, Mohamed Zahran, Li Erran Li, Mohamed Elhoseiny. [doi]
- Efficient Conformal Prediction via Cascaded Inference with Expanded AdmissionAdam Fisch, Tal Schuster, Tommi S. Jaakkola, Regina Barzilay. [doi]
- Contemplating Real-World Object ClassificationAli Borji. [doi]
- Dance Revolution: Long-Term Dance Generation with Music via Curriculum LearningRuozi Huang, Huang Hu, Wei Wu, Kei Sawada, Mi Zhang, Daxin Jiang. [doi]
- Group Equivariant Stand-Alone Self-Attention For VisionDavid W. Romero, Jean-Baptiste Cordonnier. [doi]
- Isometric Transformation Invariant and Equivariant Graph Convolutional NetworksMasanobu Horie, Naoki Morita, Toshiaki Hishinuma, Yu Ihara, Naoto Mitsume. [doi]
- Learning-based Support Estimation in Sublinear TimeTalya Eden, Piotr Indyk, Shyam Narayanan, Ronitt Rubinfeld, Sandeep Silwal, Tal Wagner. [doi]
- Meta-learning with negative learning ratesAlberto Bernacchia. [doi]
- Latent Skill Planning for Exploration and TransferKevin Xie, Homanga Bharadhwaj, Danijar Hafner, Animesh Garg, Florian Shkurti. [doi]
- Learning a Latent Simplex in Input Sparsity TimeAinesh Bakshi, Chiranjib Bhattacharyya, Ravi Kannan, David P. Woodruff, Samson Zhou. [doi]
- Acting in Delayed Environments with Non-Stationary Markov PoliciesEsther Derman, Gal Dalal, Shie Mannor. [doi]
- New Bounds For Distributed Mean Estimation and Variance ReductionPeter Davies, Vijaykrishna Gurunanthan, Niusha Moshrefi, Saleh Ashkboos, Dan Alistarh. [doi]
- Degree-Quant: Quantization-Aware Training for Graph Neural NetworksShyam Anil Tailor, Javier Fernández-Marques, Nicholas Donald Lane. [doi]
- Genetic Soft Updates for Policy Evolution in Deep Reinforcement LearningEnrico Marchesini, Davide Corsi, Alessandro Farinelli. [doi]
- GAN2GAN: Generative Noise Learning for Blind Denoising with Single Noisy ImagesSungmin Cha, Taeeon Park, Byeongjoon Kim, Jongduk Baek, Taesup Moon. [doi]
- Batch Reinforcement Learning Through Continuation MethodYijie Guo, Shengyu Feng, Nicolas Le Roux, Ed Chi, Honglak Lee, Minmin Chen. [doi]
- Exploring the Uncertainty Properties of Neural Networks' Implicit Priors in the Infinite-Width LimitBen Adlam, Jaehoon Lee, Lechao Xiao, Jeffrey Pennington, Jasper Snoek. [doi]
- Fantastic Four: Differentiable and Efficient Bounds on Singular Values of Convolution LayersSahil Singla 0002, Soheil Feizi. [doi]
- Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoFAtanas Mirchev, Baris Kayalibay, Patrick van der Smagt, Justin Bayer. [doi]
- Reducing the Computational Cost of Deep Generative Models with Binary Neural NetworksThomas Bird, Friso H. Kingma, David Barber. [doi]
- End-to-end Adversarial Text-to-SpeechJeff Donahue, Sander Dieleman, Mikolaj Binkowski, Erich Elsen, Karen Simonyan. [doi]
- Better Fine-Tuning by Reducing Representational CollapseArmen Aghajanyan, Akshat Shrivastava, Anchit Gupta, Naman Goyal, Luke Zettlemoyer, Sonal Gupta. [doi]
- Optimizing Memory Placement using Evolutionary Graph Reinforcement LearningShauharda Khadka, Estelle Aflalo, Mattias Marder, Avrech Ben-David, Santiago Miret, Shie Mannor, Tamir Hazan, Hanlin Tang, Somdeb Majumdar. [doi]
- Cross-Attentional Audio-Visual Fusion for Weakly-Supervised Action LocalizationJun-Tae Lee, Mihir Jain, Hyoungwoo Park, Sungrack Yun. [doi]
- R-GAP: Recursive Gradient Attack on PrivacyJunyi Zhu, Matthew B. Blaschko. [doi]
- Neural Pruning via Growing RegularizationHuan Wang, Can Qin, Yulun Zhang, Yun Fu 0001. [doi]
- The Risks of Invariant Risk MinimizationElan Rosenfeld, Pradeep Kumar Ravikumar, Andrej Risteski. [doi]
- Heteroskedastic and Imbalanced Deep Learning with Adaptive RegularizationKaidi Cao, Yining Chen, Junwei Lu, Nikos Aréchiga, Adrien Gaidon, Tengyu Ma. [doi]
- Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time AlgorithmsArda Sahiner, Tolga Ergen, John M. Pauly, Mert Pilanci. [doi]
- InfoBERT: Improving Robustness of Language Models from An Information Theoretic PerspectiveBoxin Wang, Shuohang Wang, Yu Cheng, Zhe Gan, Ruoxi Jia, Bo Li, Jingjing Liu. [doi]
- Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete VerifiersKaidi Xu, Huan Zhang, Shiqi Wang 0002, Yihan Wang, Suman Jana, Xue Lin, Cho-Jui Hsieh. [doi]
- Latent Convergent Cross MappingEdward De Brouwer, Adam Arany, Jaak Simm, Yves Moreau. [doi]
- MetaNorm: Learning to Normalize Few-Shot Batches Across DomainsYing-jun Du, Xiantong Zhen, Ling Shao 0001, Cees G. M. Snoek. [doi]
- Learning Value Functions in Deep Policy Gradients using Residual VarianceYannis Flet-Berliac, Reda Ouhamma, Odalric-Ambrym Maillard, Philippe Preux. [doi]
- On the Theory of Implicit Deep Learning: Global Convergence with Implicit LayersKenji Kawaguchi. [doi]
- Evaluating the Disentanglement of Deep Generative Models through Manifold TopologySharon Zhou, Eric Zelikman, Fred Lu, Andrew Y. Ng, Gunnar E. Carlsson, Stefano Ermon. [doi]
- When Optimizing f-Divergence is Robust with Label NoiseJiaheng Wei, Yang Liu. [doi]
- Contextual Transformation Networks for Online Continual LearningQuang Pham, Chenghao Liu, Doyen Sahoo, Steven C. H. Hoi. [doi]
- Learning continuous-time PDEs from sparse data with graph neural networksValerii Iakovlev, Markus Heinonen, Harri Lähdesmäki. [doi]
- Conservative Safety Critics for ExplorationHomanga Bharadhwaj, Aviral Kumar, Nicholas Rhinehart, Sergey Levine, Florian Shkurti, Animesh Garg. [doi]
- Accelerating Convergence of Replica Exchange Stochastic Gradient MCMC via Variance ReductionWei Deng 0002, Qi Feng, Georgios P. Karagiannis, Guang Lin, Faming Liang. [doi]
- i-Mix: A Domain-Agnostic Strategy for Contrastive Representation LearningKibok Lee, Yian Zhu, Kihyuk Sohn, Chun-Liang Li, Jinwoo Shin, Honglak Lee. [doi]
- Spatially Structured Recurrent ModulesNasim Rahaman, Anirudh Goyal, Muhammad Waleed Gondal, Manuel Wuthrich, Stefan Bauer, Yash Sharma, Yoshua Bengio, Bernhard Schölkopf. [doi]
- NBDT: Neural-Backed Decision TreeAlvin Wan, Lisa Dunlap, Daniel Ho, Jihan Yin, Scott Lee, Suzanne Petryk, Sarah Adel Bargal, Joseph E. Gonzalez. [doi]
- Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved ComplexityShaocong Ma, Ziyi Chen, Yi Zhou, Shaofeng Zou. [doi]
- For self-supervised learning, Rationality implies generalization, provablyYamini Bansal, Gal Kaplun, Boaz Barak. [doi]
- Zero-shot Synthesis with Group-Supervised LearningYunhao Ge, Sami Abu-El-Haija, Gan Xin, Laurent Itti. [doi]
- Improved Estimation of Concentration Under ℓp-Norm Distance Metrics Using Half SpacesJack Prescott, Xiao Zhang, David Evans. [doi]
- No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep NetworksShyamgopal Karthik, Ameya Prabhu, Puneet K. Dokania, Vineet Gandhi. [doi]
- Learning Better Structured Representations Using Low-rank Adaptive Label SmoothingAsish Ghoshal, Xilun Chen, Sonal Gupta, Luke Zettlemoyer, Yashar Mehdad. [doi]
- GANs Can Play Lottery Tickets TooXuxi Chen, Zhenyu Zhang, Yongduo Sui, Tianlong Chen. [doi]
- Predicting Classification Accuracy When Adding New Unobserved ClassesYuli Slavutsky, Yuval Benjamini. [doi]
- Uncertainty Sets for Image Classifiers using Conformal PredictionAnastasios Nikolas Angelopoulos, Stephen Bates, Michael I. Jordan, Jitendra Malik. [doi]
- Bypassing the Ambient Dimension: Private SGD with Gradient Subspace IdentificationYingxue Zhou, Steven Wu, Arindam Banerjee 0001. [doi]
- A teacher-student framework to distill future trajectoriesAlexander Neitz, Giambattista Parascandolo, Bernhard Schölkopf. [doi]
- Multi-Time Attention Networks for Irregularly Sampled Time SeriesSatya Narayan Shukla, Benjamin M. Marlin. [doi]
- Sequential Density Ratio Estimation for Simultaneous Optimization of Speed and AccuracyAkinori F. Ebihara, Taiki Miyagawa, Kazuyuki Sakurai, Hitoshi Imaoka. [doi]
- Learning Safe Multi-agent Control with Decentralized Neural Barrier CertificatesZengyi Qin, Kaiqing Zhang, Yuxiao Chen, Jingkai Chen, Chuchu Fan. [doi]
- CoCon: A Self-Supervised Approach for Controlled Text GenerationAlvin Chan, Yew-Soon Ong, Bill Pung, Aston Zhang, Jie Fu. [doi]
- Usable Information and Evolution of Optimal Representations During TrainingMichael Kleinman, Alessandro Achille, Daksh Idnani, Jonathan C. Kao. [doi]
- A Discriminative Gaussian Mixture Model with SparsityHideaki Hayashi, Seiichi Uchida. [doi]
- Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical StudyZhiqiang Shen, Zechun Liu, Dejia Xu, Zitian Chen, Kwang-Ting Cheng, Marios Savvides. [doi]
- BREEDS: Benchmarks for Subpopulation ShiftShibani Santurkar, Dimitris Tsipras, Aleksander Madry. [doi]
- A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat MinimaZeke Xie, Issei Sato, Masashi Sugiyama. [doi]
- Fooling a Complete Neural Network VerifierDániel Zombori, Balázs Bánhelyi, Tibor Csendes, István Megyeri, Márk Jelasity. [doi]
- Free Lunch for Few-shot Learning: Distribution CalibrationShuo Yang, Lu Liu, Min Xu. [doi]
- Non-asymptotic Confidence Intervals of Off-policy Evaluation: Primal and Dual BoundsYihao Feng, Ziyang Tang, Na Zhang, Qiang Liu 0001. [doi]
- Unsupervised Representation Learning for Time Series with Temporal Neighborhood CodingSana Tonekaboni, Danny Eytan, Anna Goldenberg. [doi]
- Lossless Compression of Structured Convolutional Models via LiftingGustav Sourek, Filip Zelezný, Ondrej Kuzelka. [doi]
- Cut out the annotator, keep the cutout: better segmentation with weak supervisionSarah M. Hooper, Michael Wornow, Ying Hang Seah, Peter Kellman, Hui Xue, Frederic Sala, Curtis Langlotz, Christopher Ré. [doi]
- CoCo: Controllable Counterfactuals for Evaluating Dialogue State TrackersShiyang Li, Semih Yavuz, Kazuma Hashimoto, Jia Li, Tong Niu, Nazneen Rajani, Xifeng Yan, Yingbo Zhou, Caiming Xiong. [doi]
- Learning Structural Edits via Incremental Tree TransformationsZiyu Yao, Frank F. Xu, Pengcheng Yin, Huan Sun, Graham Neubig. [doi]
- Domain Generalization with MixStyleKaiyang Zhou, Yongxin Yang, Yu Qiao 0001, Tao Xiang. [doi]
- Teaching Temporal Logics to Neural NetworksChristopher Hahn, Frederik Schmitt, Jens U. Kreber, Markus Norman Rabe, Bernd Finkbeiner. [doi]
- Efficient Generalized Spherical CNNsOliver J. Cobb, Christopher G. R. Wallis, Augustine N. Mavor-Parker, Augustin Marignier, Matthew A. Price, Mayeul d'Avezac, Jason D. McEwen. [doi]
- Understanding the role of importance weighting for deep learningDa Xu, Yuting Ye, Chuanwei Ruan. [doi]
- Grounding Language to Autonomously-Acquired Skills via Goal GenerationAhmed Akakzia, Cédric Colas, Pierre-Yves Oudeyer, Mohamed Chetouani, Olivier Sigaud. [doi]
- Deconstructing the Regularization of BatchNormYann Dauphin, Ekin Dogus Cubuk. [doi]
- LEAF: A Learnable Frontend for Audio ClassificationNeil Zeghidour, Olivier Teboul, Félix de Chaumont Quitry, Marco Tagliasacchi. [doi]
- Deep Neural Network Fingerprinting by Conferrable Adversarial ExamplesNils Lukas, Yuxuan Zhang, Florian Kerschbaum. [doi]
- When does preconditioning help or hurt generalization?Shun-ichi Amari, Jimmy Ba, Roger Baker Grosse, Xuechen Li, Atsushi Nitanda, Taiji Suzuki, Denny Wu, Ji Xu. [doi]
- VCNet and Functional Targeted Regularization For Learning Causal Effects of Continuous TreatmentsLizhen Nie, Mao Ye, Qiang Liu 0001, Dan Nicolae. [doi]
- A Learning Theoretic Perspective on Local ExplainabilityJeffrey Li, Vaishnavh Nagarajan, Gregory Plumb, Ameet Talwalkar. [doi]
- Dynamic Tensor RematerializationMarisa Kirisame, Steven Lyubomirsky, Altan Haan, Jennifer Brennan, Mike He, Jared Roesch, TianQi Chen, Zachary Tatlock. [doi]
- AdaGCN: Adaboosting Graph Convolutional Networks into Deep ModelsKe Sun, Zhanxing Zhu, Zhouchen Lin. [doi]
- Auction Learning as a Two-Player GameJad Rahme, Samy Jelassi, S. Matthew Weinberg. [doi]
- Progressive Skeletonization: Trimming more fat from a network at initializationPau de Jorge, Amartya Sanyal, Harkirat S. Behl, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania. [doi]
- Local Convergence Analysis of Gradient Descent Ascent with Finite Timescale SeparationTanner Fiez, Lillian J. Ratliff. [doi]
- Attentional Constellation Nets for Few-Shot LearningWeijian Xu, Yifan Xu, Huaijin Wang, Zhuowen Tu. [doi]
- Sharper Generalization Bounds for Learning with Gradient-dominated Objective FunctionsYunwen Lei, Yiming Ying. [doi]
- Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradientsBrenden K. Petersen, Mikel Landajuela Larma, Terrell N. Mundhenk, Cláudio Prata Santiago, Sookyung Kim, Joanne Taery Kim. [doi]
- Few-Shot Bayesian Optimization with Deep Kernel SurrogatesMartin Wistuba, Josif Grabocka. [doi]
- On Data-Augmentation and Consistency-Based Semi-Supervised LearningAtin Ghosh, Alexandre H. Thiery. [doi]
- IDF++: Analyzing and Improving Integer Discrete Flows for Lossless CompressionRianne van den Berg, Alexey A. Gritsenko, Mostafa Dehghani 0001, Casper Kaae Sønderby, Tim Salimans. [doi]
- On the mapping between Hopfield networks and Restricted Boltzmann MachinesMatthew Smart, Anton Zilman. [doi]
- What Can You Learn From Your Muscles? Learning Visual Representation from Human InteractionsKiana Ehsani, Daniel Gordon, Thomas Hai Dang Nguyen, Roozbeh Mottaghi, Ali Farhadi. [doi]
- Robust early-learning: Hindering the memorization of noisy labelsXiaobo Xia, Tongliang Liu, Bo Han 0003, Chen Gong 0002, Nannan Wang, ZongYuan Ge, Yi Chang. [doi]
- Randomized Ensembled Double Q-Learning: Learning Fast Without a ModelXinyue Chen, Che Wang, Zijian Zhou, Keith W. Ross. [doi]
- Knowledge Distillation as Semiparametric InferenceTri Dao, Govinda M. Kamath, Vasilis Syrgkanis, Lester Mackey. [doi]
- Efficient Wasserstein Natural Gradients for Reinforcement LearningTed Moskovitz, Michael Arbel, Ferenc Huszar, Arthur Gretton. [doi]
- Learning Subgoal Representations with Slow DynamicsSiyuan Li, Lulu Zheng, Jianhao Wang, Chongjie Zhang. [doi]
- Contextual Dropout: An Efficient Sample-Dependent Dropout ModuleXinjie Fan, Shujian Zhang, Korawat Tanwisuth, Xiaoning Qian, Mingyuan Zhou. [doi]
- Reinforcement Learning with Random DelaysYann Bouteiller, Simon Ramstedt, Giovanni Beltrame, Christopher J. Pal, Jonathan Binas. [doi]
- Wandering within a world: Online contextualized few-shot learningMengye Ren, Michael Louis Iuzzolino, Michael Curtis Mozer, Richard S. Zemel. [doi]
- What Should Not Be Contrastive in Contrastive LearningTete Xiao, Xiaolong Wang 0004, Alexei A. Efros, Trevor Darrell. [doi]
- Learning Task-General Representations with Generative Neuro-Symbolic ModelingReuben Feinman, Brenden M. Lake. [doi]
- Variational Information Bottleneck for Effective Low-Resource Fine-TuningRabeeh Karimi Mahabadi, Yonatan Belinkov, James Henderson. [doi]
- Coping with Label Shift via Distributionally Robust OptimisationJingzhao Zhang, Aditya Krishna Menon, Andreas Veit, Srinadh Bhojanapalli, Sanjiv Kumar, Suvrit Sra. [doi]
- Tilted Empirical Risk MinimizationTian Li 0005, Ahmad Beirami, Maziar Sanjabi, Virginia Smith. [doi]
- Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired PerspectiveWuyang Chen, Xinyu Gong, Zhangyang Wang. [doi]
- Isotropy in the Contextual Embedding Space: Clusters and ManifoldsXingyu Cai, Jiaji Huang, Yuchen Bian, Kenneth Church 0001. [doi]
- Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature VisualizationJudy Borowski, Roland Simon Zimmermann, Judith Schepers, Robert Geirhos, Thomas S. A. Wallis, Matthias Bethge, Wieland Brendel. [doi]
- Chaos of Learning Beyond Zero-sum and Coordination via Game DecompositionsYun Kuen Cheung, Yixin Tao. [doi]
- Deciphering and Optimizing Multi-Task Learning: a Random Matrix ApproachMalik Tiomoko, Hafiz Tiomoko Ali, Romain Couillet. [doi]
- Learning a Latent Search Space for Routing Problems using Variational AutoencodersAndré Hottung, Bhanu Bhandari, Kevin Tierney. [doi]
- Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown DynamicsYanchao Sun, Da Huo, Furong Huang. [doi]
- Offline Model-Based Optimization via Normalized Maximum Likelihood EstimationJustin Fu, Sergey Levine. [doi]
- Interpreting Knowledge Graph Relation Representation from Word EmbeddingsCarl Allen, Ivana Balazevic, Timothy M. Hospedales. [doi]
- Shape-Texture Debiased Neural Network TrainingYingwei Li, Qihang Yu, Mingxing Tan, Jieru Mei, Peng Tang, Wei Shen 0002, Alan L. Yuille, Cihang Xie. [doi]
- Learning Accurate Entropy Model with Global Reference for Image CompressionYichen Qian, Zhiyu Tan, Xiuyu Sun, Ming Lin, Dongyang Li, Zhenhong Sun, Li Hao, Rong Jin. [doi]
- Unlearnable Examples: Making Personal Data UnexploitableHanxun Huang, Xingjun Ma, Sarah Monazam Erfani, James Bailey 0001, Yisen Wang 0001. [doi]
- Relating by Contrasting: A Data-efficient Framework for Multimodal Generative ModelsYuge Shi, Brooks Paige, Philip H. S. Torr, N. Siddharth 0001. [doi]
- Decentralized Attribution of Generative ModelsChanghoon Kim, Yi Ren, Yezhou Yang. [doi]
- Fast And Slow Learning Of Recurrent Independent MechanismsKanika Madan, Nan Rosemary Ke, Anirudh Goyal, Bernhard Schölkopf, Yoshua Bengio. [doi]
- LiftPool: Bidirectional ConvNet PoolingJiaojiao Zhao, Cees G. M. Snoek. [doi]
- Can a Fruit Fly Learn Word Embeddings?Yuchen Liang, Chaitanya K. Ryali, Benjamin Hoover, Leopold Grinberg, Saket Navlakha, Mohammed J. Zaki, Dmitry Krotov. [doi]
- Transformer protein language models are unsupervised structure learnersRoshan Rao, Joshua Meier, Tom Sercu, Sergey Ovchinnikov, Alexander Rives. [doi]
- Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel RegimeAtsushi Nitanda, Taiji Suzuki. [doi]
- On the Dynamics of Training Attention ModelsHaoye Lu, Yongyi Mao, Amiya Nayak. [doi]
- Generalized Energy Based ModelsMichael Arbel, Liang Zhou, Arthur Gretton. [doi]
- Learning Neural Event Functions for Ordinary Differential EquationsRicky T. Q. Chen, Brandon Amos, Maximilian Nickel. [doi]
- Learning with Instance-Dependent Label Noise: A Sample Sieve ApproachHao Cheng, Zhaowei Zhu, Xingyu Li, Yifei Gong, Xing Sun, Yang Liu. [doi]
- Robust Curriculum Learning: from clean label detection to noisy label self-correctionTianyi Zhou, Shengjie Wang, Jeff A. Bilmes. [doi]
- Individually Fair RankingsAmanda Bower, Hamid Eftekhari, Mikhail Yurochkin, Yuekai Sun. [doi]
- Disentangling 3D Prototypical Networks for Few-Shot Concept LearningMihir Prabhudesai, Shamit Lal, Darshan Patil, Hsiao-Yu Tung, Adam W. Harley, Katerina Fragkiadaki. [doi]
- Contrastive Syn-to-Real GeneralizationWuyang Chen, Zhiding Yu, Shalini De Mello, Sifei Liu, Jose M. Alvarez, Zhangyang Wang, Anima Anandkumar. [doi]
- Factorizing Declarative and Procedural Knowledge in Structured, Dynamical EnvironmentsAnirudh Goyal, Alex Lamb, Phanideep Gampa, Philippe Beaudoin, Charles Blundell, Sergey Levine, Yoshua Bengio, Michael Curtis Mozer. [doi]
- Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on ImagesRewon Child. [doi]
- Rethinking Embedding Coupling in Pre-trained Language ModelsHyung Won Chung, Thibault Févry, Henry Tsai, Melvin Johnson, Sebastian Ruder. [doi]
- Predicting Inductive Biases of Pre-Trained ModelsCharles Lovering, Rohan Jha, Tal Linzen, Ellie Pavlick. [doi]
- Model-Based Offline PlanningArthur Argenson, Gabriel Dulac-Arnold. [doi]
- Private Image Reconstruction from System Side Channels Using Generative ModelsYuanyuan Yuan, Shuai Wang, Junping Zhang. [doi]
- Representation Learning via Invariant Causal MechanismsJovana Mitrovic, Brian McWilliams, Jacob C. Walker, Lars Holger Buesing, Charles Blundell. [doi]