Abstract is missing.
- Synthesizing Audio with GANsChris Donahue, Julian McAuley, Miller Puckette. [doi]
- Causal Discovery Using Proxy VariablesMateo Rojas-Carulla, Marco Baroni, David Lopez-Paz. [doi]
- Faster Neural Networks Straight from JPEGLionel Gueguen, Alex Sergeev, Rosanne Liu, Jason Yosinski. [doi]
- Rotational Unit of MemoryRumen Dangovski, Li Jing, Marin Soljacic. [doi]
- TransNets for Review GenerationRose Catherine, William W. Cohen. [doi]
- Uncertainty Estimation via Stochastic Batch NormalizationAndrei Atanov, Arsenii Ashukha, Dmitry Molchanov, Kirill Neklyudov, Dmitry P. Vetrov. [doi]
- Learning Rich Image Representation with Deep Layer AggregationFisher Yu, Dequan Wang, Evan Shelhamer, Trevor Darrell. [doi]
- Wasserstein Auto-Encoders: Latent Dimensionality and Random EncodersPaul K. Rubenstein, Bernhard Schölkopf, Ilya O. Tolstikhin. [doi]
- Differentiable Neural Network Architecture SearchRichard Shin, Charles Packer, Dawn Song. [doi]
- Are Efficient Deep Representations Learnable?Maxwell Nye, Andrew Saxe. [doi]
- Adversarial SpheresJustin Gilmer, Luke Metz, Fartash Faghri, Samuel S. Schoenholz, Maithra Raghu, Martin Wattenberg, Ian J. Goodfellow. [doi]
- Graph Partition Neural Networks for Semi-Supervised ClassificationRenjie Liao, Marc Brockschmidt, Daniel Tarlow, Alexander L. Gaunt, Raquel Urtasun, Richard S. Zemel. [doi]
- Fast and Accurate Text Classification: Skimming, Rereading and Early StoppingKeyi Yu, Yang Liu 0097, Alexander G. Schwing, Jian Peng 0001. [doi]
- Additive Margin Softmax for Face VerificationFeng Wang 0015, Weiyang Liu, Hanjun Dai, Haijun Liu, Jian Cheng 0003. [doi]
- Combating Adversarial Attacks Using Sparse RepresentationsSoorya Gopalakrishnan, Zhinus Marzi, Upamanyu Madhow, Ramtin Pedarsani. [doi]
- A Dataset To Evaluate The Representations Learned By Video Prediction ModelsRyan Szeto, Simon Stent, Germán Ros, Jason J. Corso. [doi]
- The Effectiveness of a two-Layer Neural Network for RecommendationsOleg Rybakov, Vijai Mohan, Avishkar Misra, Scott Legrand, Rejith Joseph, Kiuk Chung, Siddharth Singh, Qian You, Eric T. Nalisnick, Leo Dirac, Runfei Luo. [doi]
- Regularization Neural Networks via Constrained Virtual Movement FieldZhendong Zhang, Cheolkon Jung. [doi]
- Comparing Fixed and Adaptive Computation Time for Recurrent Neural NetworksDaniel Fojo, Víctor Campos, Xavier Giró i Nieto. [doi]
- FigureQA: An Annotated Figure Dataset for Visual ReasoningSamira Ebrahimi Kahou, Vincent Michalski, Adam Atkinson, Ákos Kádár, Adam Trischler, Yoshua Bengio. [doi]
- Variance-based Gradient Compression for Efficient Distributed Deep LearningYusuke Tsuzuku, Hiroto Imachi, Takuya Akiba. [doi]
- Weightless: Lossy weight encoding for deep neural network compressionBrandon Reagen, Udit Gupta, Robert Adolf, Michael Mitzenmacher, Alexander M. Rush, Gu-Yeon Wei, David Brooks 0001. [doi]
- Depth separation and weight-width trade-offs for sigmoidal neural networksAmit Deshpande 0001, Navin Goyal, Sushrut Karmalkar. [doi]
- Minimally Redundant Laplacian EigenmapsDavid Pfau, Christopher P. Burgess. [doi]
- Coupled Ensembles of Neural NetworksAnuvabh Dutt, Denis Pellerin, Georges Quénot. [doi]
- Towards Specification-Directed Program RepairRichard Shin, Illia Polosukhin, Dawn Song. [doi]
- Practical Hyperparameter Optimization for Deep LearningStefan Falkner, Aaron Klein, Frank Hutter. [doi]
- Resilient Backpropagation (Rprop) for Batch-learning in TensorFlowCiprian Florescu, Christian Igel. [doi]
- Concept Learning with Energy-Based ModelsIgor Mordatch. [doi]
- An interpretable LSTM neural network for autoregressive exogenous modelTian Guo, Tao Lin, Yao Lu. [doi]
- Evaluating visual "common sense" using fine-grained classification and captioning tasksRaghav Goyal, Farzaneh Mahdisoltani, Guillaume Berger, Waseem Gharbieh, Ingo Bax, Roland Memisevic. [doi]
- Investigating Human Priors for Playing Video GamesRachit Dubey, Pulkit Agarwal, Deepak Pathak, Alyosha A. Efros, Thomas L. Griffiths. [doi]
- Analysis of Cosmic Microwave Background with Deep LearningSiyu He, Siamak Ravanbakhsh, Shirley Ho. [doi]
- Towards Variational Generation of Small GraphsMartin Simonovsky, Nikos Komodakis. [doi]
- Inference in probabilistic graphical models by Graph Neural NetworksKiJung Yoon, Renjie Liao, Yuwen Xiong, Lisa Zhang, Ethan Fetaya, Raquel Urtasun, Richard S. Zemel, Xaq Pitkow. [doi]
- Decoupling Dynamics and Reward for Transfer LearningAmy Zhang, Harsh Satija, Joelle Pineau. [doi]
- An Evaluation of Fisher Approximations Beyond Kronecker FactorizationCésar Laurent, Thomas George, Xavier Bouthillier, Nicolas Ballas, Pascal Vincent. [doi]
- IamNN: Iterative and Adaptive Mobile Neural Network for efficient image classificationSam Leroux, Pavlo Molchanov, Pieter Simoens, Bart Dhoedt, Thomas Breuel, Jan Kautz. [doi]
- Iterative GANs for Rotating Visual ObjectsYsbrand Galama, Thomas Mensink. [doi]
- GeoSeq2Seq: Information Geometric Sequence-to-Sequence NetworksAlessandro Bay, Biswa Sengupta. [doi]
- Predict Responsibly: Increasing Fairness by Learning to DeferDavid Madras, Toniann Pitassi, Richard S. Zemel. [doi]
- Jointly Learning "What" and "How" from Instructions and Goal-StatesDzmitry Bahdanau, Felix Hill, Jan Leike, Edward Hughes, Pushmeet Kohli, Edward Grefenstette. [doi]
- Rethinking Style and Content Disentanglement in Variational AutoencodersRui Shu, Shengjia Zhao, Mykel J. Kochenderfer. [doi]
- 3D-Scene-GAN: Three-dimensional Scene Reconstruction with Generative Adversarial NetworksChong Yu, Young Wang. [doi]
- Censoring Representations with Multiple-Adversaries over Random SubspacesYusuke Iwasawa, Kotaro Nakayama, Yutaka Matsuo. [doi]
- Learning to Organize Knowledge with N-Gram MachinesFan Yang, Jiazhong Nie, William W. Cohen, Ni Lao. [doi]
- Meta-Learning a Dynamical Language ModelThomas Wolf, Julien Chaumond, Clement Delangue. [doi]
- Reward Estimation for Variance Reduction in Deep Reinforcement LearningJoshua Romoff, Alexandre Piché, Peter Henderson 0002, Vincent François-Lavet, Joelle Pineau. [doi]
- Deep learning mutation prediction enables early stage lung cancer detection in liquid biopsySteven T. Kothen-Hill, Asaf Zviran, Rafael C. Schulman, Sunil Deochand, Federico Gaiti, Dillon Maloney, Kevin Y. Huang, Will Liao, Nicolas Robine, Nathaniel D. Omans, Dan A. Landau. [doi]
- Adaptive Memory NetworksDaniel Li, Asim Kadav. [doi]
- Realistic Evaluation of Semi-Supervised Learning AlgorithmsAvital Oliver, Augustus Odena, Colin Raffel, Ekin D. Cubuk, Ian J. Goodfellow. [doi]
- HoME: a Household Multimodal EnvironmentSimon Brodeur, Ethan Perez, Ankesh Anand, Florian Golemo, Luca Celotti, Florian Strub, Jean Rouat, Hugo Larochelle, Aaron C. Courville. [doi]
- Learning to Learn Without LabelsLuke Metz, Niru Maheswaranathan, Brian Cheung, Jascha Sohl-Dickstein. [doi]
- Training Shallow and Thin Networks for Acceleration via Knowledge Distillation with Conditional Adversarial NetworksZheng Xu 0002, Yen-Chang Hsu, Jiawei Huang. [doi]
- Conditional Networks for Few-Shot Semantic SegmentationKate Rakelly, Evan Shelhamer, Trevor Darrell, Alyosha A. Efros, Sergey Levine. [doi]
- Fast Node Embeddings: Learning Ego-Centric RepresentationsTiago Pimentel, Adriano Veloso, Nivio Ziviani. [doi]
- Learning Longer-term Dependencies in RNNs with Auxiliary LossesTrieu H. Trinh, Andrew M. Dai, Minh-Thang Luong, Quoc V. Le. [doi]
- Parametric Adversarial Divergences are Good Task Losses for Generative ModelingGabriel Huang, Hugo Berard, Ahmed Touati, Gauthier Gidel, Pascal Vincent, Simon Lacoste-Julien. [doi]
- Adversarial Policy Gradient for Alternating Markov GamesChao Gao, Martin Müller 0003, Ryan Hayward. [doi]
- Tempered Adversarial NetworksMehdi S. M. Sajjadi, Giambattista Parascandolo, Arash Mehrjou, Bernhard Schölkopf. [doi]
- One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-LearningTianhe Yu, Chelsea Finn, Annie Xie, Sudeep Dasari, Tianhao Zhang, Pieter Abbeel, Sergey Levine. [doi]
- Automated Design using Neural Networks and Gradient DescentOliver Hennigh. [doi]
- Systematic Weight Pruning of DNNs using Alternating Direction Method of MultipliersTianyun Zhang, Shaokai Ye, Yipeng Zhang, Yanzhi Wang, Makan Fardad. [doi]
- Stochastic Gradient Langevin dynamics that Exploit Neural Network StructureZachary Nado, Jasper Snoek, Roger Grosse, David Duvenaud, Bowen Xu, James Martens. [doi]
- Convolutional Sequence Modeling RevisitedShaojie Bai, J. Zico Kolter, Vladlen Koltun. [doi]
- GitGraph - from Computational Subgraphs to Smaller Architecture Search SpacesKamil Bennani-Smires, Claudiu Musat, Andreea Hossmann, Michael Baeriswyl. [doi]
- ComboGAN: Unrestricted Scalability for Image Domain TranslationAsha Anoosheh, Eirikur Agustsson, Radu Timofte. [doi]
- Learning via social awareness: improving sketch representations with facial feedbackNatasha Jaques, Jesse Engel, David Ha, Fred Bertsch, Rosalind W. Picard, Douglas Eck. [doi]
- A moth brain learns to read MNISTCharles B. Delahunt, J. Nathan Kutz. [doi]
- Compression by the signs: distributed learning is a two-way streetJeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, Anima Anandkumar. [doi]
- Distributional Adversarial NetworksChengtao Li, David Alvarez-Melis, Keyulu Xu, Stefanie Jegelka, Suvrit Sra. [doi]
- Neural network parameter regression for lattice quantum chromodynamics simulations in nuclear and particle physicsPhiala Shanahan, Daniel Trewartha, William Detmold. [doi]
- Stacked Filters Stationary Flow For Hardware-Oriented Acceleration Of Deep Convolutional Neural NetworksYuechao Gao, Nianhong Liu, Sheng Zhang. [doi]
- Scalable Estimation via LSH Samplers (LSS)Ryan Spring, Anshumali Shrivastava. [doi]
- Feature Incay for Representation RegularizationYuhui Yuan, Kuiyuan Yang, Jianyuan Guo, Chao Zhang, Jingdong Wang. [doi]
- DeepNCM: Deep Nearest Class Mean ClassifiersSamantha Guerriero, Barbara Caputo, Thomas Mensink. [doi]
- Stable and Effective Trainable Greedy Decoding for Sequence to Sequence LearningYun Chen, KyungHyun Cho, Samuel R. Bowman, Victor O. K. Li. [doi]
- Reinforcement Learning from Imperfect DemonstrationsYang Gao, Huazhe Xu, Ji Lin, Fisher Yu, Sergey Levine, Trevor Darrell. [doi]
- Learning Deep Models: Critical Points and Local OpennessMaher Nouiehed, Meisam Razaviyayn. [doi]
- Multiple Source Domain Adaptation with Adversarial LearningHan Zhao 0002, Shanghang Zhang, Guanhang Wu, João P. Costeira, José M. F. Moura, Geoffrey J. Gordon. [doi]
- Extending the Framework of Equilibrium Propagation to General DynamicsBenjamin Scellier, Anirudh Goyal, Jonathan Binas, Thomas Mesnard, Yoshua Bengio. [doi]
- Gradients explode - Deep Networks are shallow - ResNet explainedGeorge Philipp, Dawn Song, Jaime G. Carbonell. [doi]
- Gradient-based Optimization of Neural Network ArchitectureWill Grathwohl, Elliot Creager, Seyed Kamyar Seyed Ghasemipour, Richard S. Zemel. [doi]
- Extending Robust Adversarial Reinforcement Learning Considering Adaptation and DiversityHiroaki Shioya, Yusuke Iwasawa, Yutaka Matsuo. [doi]
- Expert-based reward function training: the novel method to train sequence generatorsJoji Toyama, Yusuke Iwasawa, Kotaro Nakayama, Yutaka Matsuo. [doi]
- Reconstructing evolutionary trajectories of mutations in cancerYulia Rubanova, Ruian Shi, Roujia Li, Jeff Wintersinger, Amit G. Deshwar, Nil Sahin, Quaid Morris. [doi]
- Semi-Supervised Learning With GANs: Revisiting Manifold RegularizationBruno Lecouat, Chuan-Sheng Foo, Houssam Zenati, Vijay Ramaseshan Chandrasekhar. [doi]
- Negative eigenvalues of the Hessian in deep neural networksGuillaume Alain, Nicolas Le Roux, Pierre-Antoine Manzagol. [doi]
- A Flexible Approach to Automated RNN Architecture GenerationMartin Schrimpf, Stephen Merity, James Bradbury 0002, Richard Socher. [doi]
- Understanding the Loss Surface of Single-Layered Neural Networks for Binary ClassificationShiyu Liang, Ruoyu Sun, Yixuan Li, R. Srikant. [doi]
- Aspect-based Question GenerationWenpeng Hu, Bing Liu, Jinwen Ma, Dongyan Zhao 0001, Rui Yan. [doi]
- Adapting to Continuously Shifting DomainsAndreea Bobu, Eric Tzeng, Judy Hoffman, Trevor Darrell. [doi]
- Challenges in Disentangling Independent Factors of VariationAttila Szabó, Qiyang Hu, Tiziano Portenier, Matthias Zwicker, Paolo Favaro. [doi]
- Autoregressive Generative Adversarial NetworksYasin Yazici, Kim-Hui Yap, Stefan Winkler 0001. [doi]
- Semiparametric Reinforcement LearningMika Sarkin Jain, Jack Lindsey. [doi]
- Lsh-Sampling breaks the Computational chicken-and-egg Loop in adaptive stochastic Gradient estimationBeidi Chen, Yingchen Xu, Anshumali Shrivastava. [doi]
- Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential EquationsYiping Lu, Aoxiao Zhong, Quanzheng Li, Bin Dong. [doi]
- Learning How Not to Act in Text-based GamesMatan Haroush, Tom Zahavy, Daniel J. Mankowitz, Shie Mannor. [doi]
- Generative Modeling for Protein StructuresNamrata Anand, Possu Huang. [doi]
- To Prune, or Not to Prune: Exploring the Efficacy of Pruning for Model CompressionMichael Zhu, Suyog Gupta. [doi]
- Leveraging Constraint Logic Programming for Neural Guided Program SynthesisLisa Zhang, Gregory Rosenblatt, Ethan Fetaya, Renjie Liao, William E. Byrd, Raquel Urtasun, Richard S. Zemel. [doi]
- PixelSNAIL: An Improved Autoregressive Generative ModelXi Chen 0022, Nikhil Mishra, Mostafa Rohaninejad, Pieter Abbeel. [doi]
- Meta-Learning for Batch Mode Active LearningSachin Ravi, Hugo Larochelle. [doi]
- Learning Invariances for Policy GeneralizationRemi Tachet des Combes, Philip Bachman, Harm van Seijen. [doi]
- ChatPainter: Improving Text to Image Generation using DialogueShikhar Sharma, Dendi Suhubdy, Vincent Michalski, Samira Ebrahimi Kahou, Yoshua Bengio. [doi]
- Deep Convolutional Malware Classifiers Can Learn from Raw Executables and Labels OnlyMarek Krcál, Ondrej Svec, Martin Bálek, Otakar Jasek. [doi]
- Faster Discovery of Neural Architectures by Searching for Paths in a Large ModelHieu Pham, Melody Y. Guan, Barret Zoph, Quoc V. Le, Jeff Dean. [doi]
- Feature-Based Metrics for Exploring the Latent Space of Generative ModelsSamuli Laine. [doi]
- eCommerceGAN: A Generative Adversarial Network for e-commerceAshutosh Kumar, Arijit Biswas, Subhajit Sanyal. [doi]
- Exploring Deep Recurrent Models with Reinforcement Learning for Molecule DesignDaniel Neil, Marwin H. S. Segler, Laura Guasch, Mohamed Ahmed, Dean Plumbley, Matthew Sellwood, Nathan Brown. [doi]
- Semi-Supervised Few-Shot Learning with MAMLRinu Boney, Alexander Ilin. [doi]
- On the Limitation of Local Intrinsic Dimensionality for Characterizing the Subspaces of Adversarial ExamplesPei-Hsuan Lu, Pin-Yu Chen, Chia-Mu Yu. [doi]
- Multi-Agent Generative Adversarial Imitation LearningJiaming Song, Hongyu Ren, Dorsa Sadigh, Stefano Ermon. [doi]
- Learning Efficient Tensor Representations with Ring Structure NetworksQibin Zhao, Masashi Sugiyama, Longhao Yuan, Andrzej Cichocki. [doi]
- Spatially Parallel ConvolutionsPeter H. Jin, Boris Ginsburg, Kurt Keutzer. [doi]
- Empirical Analysis of the Hessian of Over-Parametrized Neural NetworksLevent Sagun, Utku Evci, V. Ugur Güney, Yann Dauphin, Léon Bottou. [doi]
- An Experimental Study of Neural Networks for Variable GraphsXavier Bresson, Thomas Laurent 0001. [doi]
- Monotonic models for real-time dynamic malware detectionAlexander Chistyakov, Ekaterina Lobacheva, Alexander Shevelev, Alexey Romanenko. [doi]
- Intriguing Properties of Adversarial ExamplesEkin Dogus Cubuk, Barret Zoph, Samuel S. Schoenholz, Quoc V. Le. [doi]
- SufiSent - Universal Sentence Representations Using Suffix EncodingsSiddhartha Brahma. [doi]
- NAM - Unsupervised Cross-Domain Image Mapping without Cycles or GANsYedid Hoshen, Lior Wolf. [doi]
- Covariant Compositional Networks For Learning GraphsRisi Kondor, Hy Truong Son, Horace Pan, Brandon M. Anderson, Shubhendu Trivedi. [doi]
- Can Deep Reinforcement Learning solve Erdos-Selfridge-Spencer Games?Maithra Raghu, Alex Irpan, Jacob Andreas, Robert Kleinberg, Quoc V. Le, Jon M. Kleinberg. [doi]
- Learning to InferJoseph Marino, Yisong Yue, Stephan Mandt. [doi]
- A Language and Compiler View on Differentiable ProgrammingFei Wang, Tiark Rompf. [doi]
- Predicting Embryo Morphokinetics in Videos with Late Fusion Nets & Dynamic DecodersNathan H. Ng, Julian McAuley, Julian Gingold, Nina Desai, Zachary C. Lipton. [doi]
- Deep Neural MapsMehran Pesteie, Purang Abolmaesumi, Robert Rohling. [doi]
- SpectralWords: Spectral Embeddings Approach to Word Similarity Task for Large VocabulariesIvan Lobov. [doi]
- Towards Mixed-initiative generation of multi-channel sequential structureCheng-Zhi Anna Huang, Sherol Chen, Mark J. Nelson, Douglas Eck. [doi]
- Selecting the Best in GANs Family: a Post Selection Inference FrameworkYao-Hung Hubert Tsai, Denny Wu, Makoto Yamada, Ruslan Salakhutdinov, Ichiro Takeuchi, Kenji Fukumizu. [doi]
- Pelee: A Real-Time Object Detection System on Mobile DevicesRobert J. Wang, Xiang Li 0012, Shuang Ao, Charles X. Ling. [doi]
- A differentiable BLEU loss. Analysis and first resultsNoe Casas, José A. R. Fonollosa, Marta R. Costa-Jussà. [doi]
- Regret Minimization for Partially Observable Deep Reinforcement LearningPeter H. Jin, Sergey Levine, Kurt Keutzer. [doi]
- No Spurious Local Minima in a Two Hidden Unit ReLU NetworkChenwei Wu, Jiajun Luo, Jason D. Lee. [doi]
- Winner's Curse? On Pace, Progress, and Empirical RigorD. Sculley, Jasper Snoek, Alexander B. Wiltschko, Ali Rahimi. [doi]
- Policy Optimization with Second-Order Advantage InformationJiajin Li, Baoxiang Wang. [doi]
- The loss surface and expressivity of deep convolutional neural networksQuynh Nguyen, Matthias Hein 0001. [doi]
- Learning Representations and Generative Models for 3D Point CloudsPanos Achlioptas, Olga Diamanti, Ioannis Mitliagkas, Leonidas J. Guibas. [doi]
- Attacking the Madry Defense Model with $L_1$-based Adversarial ExamplesYash Sharma, Pin-Yu Chen. [doi]
- Searching for Activation FunctionsPrajit Ramachandran, Barret Zoph, Quoc V. Le. [doi]
- Easing non-convex optimization with neural networksDavid Lopez-Paz, Levent Sagun. [doi]
- Efficient Recurrent Neural Networks using Structured Matrices in FPGAsZhe Li 0001, Shuo Wang, Caiwen Ding, Qinru Qiu, Yanzhi Wang, Yun Liang 0001. [doi]
- GILBO: One Metric to Measure Them AllAlexander A. Alemi, Ian Fischer. [doi]
- Clustering Meets Implicit Generative ModelsFrancesco Locatello, Damien Vincent, Ilya O. Tolstikhin, Gunnar Rätsch, Sylvain Gelly, Bernhard Schölkopf. [doi]
- Towards Provable Control for Unknown Linear Dynamical SystemsSanjeev Arora, Elad Hazan, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang. [doi]
- Learning and Analyzing Vector Encoding of Symbolic RepresentationRoland Fernandez, Asli Çelikyilmaz, Paul Smolensky, Rishabh Singh. [doi]
- PPP-Net: Platform-aware Progressive Search for Pareto-optimal Neural ArchitecturesJin-Dong Dong, An-Chieh Cheng, Da-Cheng Juan, Wei Wei, Min Sun. [doi]
- Analyzing and Exploiting NARX Recurrent Neural Networks for Long-Term DependenciesRobert S. DiPietro, Christian Rupprecht, Nassir Navab, Gregory D. Hager. [doi]
- Universal Successor Representations for Transfer Reinforcement LearningChen Ma, Junfeng Wen, Yoshua Bengio. [doi]
- DNA-GAN: Learning Disentangled Representations from Multi-Attribute ImagesTaihong Xiao, Jiapeng Hong, Jinwen Ma. [doi]
- Neuron as an AgentShohei Ohsawa, Kei Akuzawa, Tatsuya Matsushima, Gustavo Bezerra, Yusuke Iwasawa, Hiroshi Kajino, Seiya Takenaka, Yutaka Matsuo. [doi]
- Stable Distribution Alignment Using the Dual of the Adversarial DistanceBen Usman, Kate Saenko, Brian Kulis. [doi]
- The Mirage of Action-Dependent Baselines in Reinforcement LearningGeorge Tucker, Surya Bhupatiraju, Shixiang Gu, Richard E. Turner, Zoubin Ghahramani, Sergey Levine. [doi]
- Learning and MemorizationSatrajit Chatterjee. [doi]
- Adaptive Path-Integral Approach for Representation Learning and PlanningJung-Su Ha, Young-Jin Park, Hyeok-Joo Chae, Soon-Seo Park, Han-Lim Choi. [doi]
- SGD on Random Mixtures: Private Machine Learning under Data Breach ThreatsKangwook Lee, Kyungmin Lee, Hoon Kim, Changho Suh, Kannan Ramchandran. [doi]
- Bayesian Incremental Learning for Deep Neural NetworksMax Kochurov, Timur Garipov, Dmitry Podoprikhin, Dmitry Molchanov, Arsenii Ashukha, Dmitry P. Vetrov. [doi]
- Tree-to-tree Neural Networks for Program TranslationXinyun Chen, Chang Liu, Dawn Song. [doi]
- An Optimization View on Dynamic Routing Between CapsulesDilin Wang, Qiang Liu 0001. [doi]
- LSTM Iteration Networks: An Exploration of Differentiable Path FindingLisa Lee, Emilio Parisotto, Devendra Singh Chaplot, Ruslan Salakhutdinov. [doi]
- Cold fusion: Training Seq2seq Models Together with Language ModelsAnuroop Sriram, Heewoo Jun, Sanjeev Satheesh, Adam Coates. [doi]
- ShakeDrop regularizationYoshihiro Yamada, Masakazu Iwamura, Koichi Kise. [doi]
- A Proximal Block Coordinate Descent Algorithm for Deep Neural Network TrainingTim Tsz-Kit Lau, Jinshan Zeng, Baoyuan Wu, Yuan Yao. [doi]
- Kronecker Recurrent UnitsCijo Jose, Moustapha Cissé, François Fleuret. [doi]
- DLVM: A modern compiler infrastructure for deep learning systemsRichard Wei, Lane Schwartz, Vikram S. Adve. [doi]
- 3D-FilterMap: A Compact Architecture for Deep Convolutional Neural NetworksYingzhen Yang, Jianchao Yang, Ning Xu, Wei Han 0002, Nebojsa Jojic, Thomas S. Huang. [doi]
- Neural Program Search: Solving Programming Tasks from Description and ExamplesIllia Polosukhin, Alexander Skidanov. [doi]
- Nonlinear Acceleration of CNNsDamien Scieur, Edouard Oyallon, Alexandre d'Aspremont, Francis Bach. [doi]
- Benefits of Depth for Long-Term Memory of Recurrent NetworksYoav Levine, Or Sharir, Amnon Shashua. [doi]
- Shifting Mean Activation Towards Zero with Bipolar Activation FunctionsLars Hiller Eidnes, Arild Nøkland. [doi]
- Learning Disentangled Representations with Wasserstein Auto-EncodersPaul K. Rubenstein, Bernhard Schölkopf, Ilya O. Tolstikhin. [doi]
- Time-Dependent Representation for Neural Event Sequence PredictionYang Li, Nan Du, Samy Bengio. [doi]
- Finding Flatter Minima with SGDStanislaw Jastrzebski, Zachary Kenton, Devansh Arpit, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos J. Storkey. [doi]
- DiCE: The Infinitely Differentiable Monte-Carlo EstimatorJakob N. Foerster, Gregory Farquhar, Maruan Al-Shedivat, Tim Rocktäschel, Eric P. Xing, Shimon Whiteson. [doi]
- Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter ValuesJulius Adebayo, Justin Gilmer, Ian J. Goodfellow, Been Kim. [doi]
- Isolating Sources of Disentanglement in Variational AutoencodersTian Qi Chen, Xuechen Li, Roger Grosse, David Duvenaud. [doi]
- PDE-Net: Learning PDEs from DataZichao Long, Yiping Lu, Xianzhong Ma, Bin Dong. [doi]
- Diversity-Driven Exploration Strategy for Deep Reinforcement LearningZhang-Wei Hong, Tzu-Yun Shann, Shih-Yang Su, Yi-Hsiang Chang, Chun-Yi Lee. [doi]
- Online variance-reducing optimizationNicolas Le Roux, Reza Babanezhad, Pierre-Antoine Manzagol. [doi]
- Building Generalizable Agents with a Realistic and Rich 3D EnvironmentYi Wu, Yuxin Wu, Georgia Gkioxari, Yuandong Tian. [doi]
- Ensemble Robustness and Generalization of Stochastic Deep Learning AlgorithmsTom Zahavy, Bingyi Kang, Alex Sivak, Jiashi Feng, Huan Xu, Shie Mannor. [doi]
- ReinforceWalk: Learning to Walk in Graph with Monte Carlo Tree SearchYelong Shen, Jianshu Chen, Po-Sen Huang, Yuqing Guo, Jianfeng Gao. [doi]
- Capturing Human Category Representations by Sampling in Deep Feature SpacesJoshua C. Peterson, Krisha Aghi, Jordan W. Suchow, Alexander Y. Ku, Tom Griffiths. [doi]
- Accelerating Neural Architecture Search using Performance PredictionBowen Baker, Otkrist Gupta, Ramesh Raskar, Nikhil Naik. [doi]
- Exponentially vanishing sub-optimal local minima in multilayer neural networksDaniel Soudry, Elad Hoffer. [doi]
- Hockey-Stick GANEdgar Minasyan, Vinay Prabhu. [doi]
- Learning Invariance with Compact TransformsAnna T. Thomas, Albert Gu, Tri Dao, Atri Rudra, Christopher Ré. [doi]
- Efficient Entropy For Policy Gradient with Multi-Dimensional Action SpaceYiming Zhang, Quan Ho Vuong, Kenny Song, Xiao-Yue Gong, Keith W. Ross. [doi]
- Simple and efficient architecture search for Convolutional Neural NetworksThomas Elsken, Jan Hendrik Metzen, Frank Hutter. [doi]
- Weighted Geodesic Distance Following Fermat's PrincipleFacundo Sapienza, Pablo Groisman, Matthieu Jonckheere. [doi]
- In reinforcement learning, all objective functions are not equalRomain Laroche, Harm van Seijen. [doi]
- Decoding Decoders: Finding Optimal Representation Spaces for Unsupervised Similarity TasksVitalii Zhelezniak, Dan Busbridge, April Shen, Samuel L. Smith, Nils Y. Hammerla. [doi]
- Designing Efficient Neural Attention Systems Towards Achieving Human-level Sharp VisionAbdul Rahman Abdul Ghani, Nishanth Koganti, Alfredo Solano, Yusuke Iwasawa, Kotaro Nakayama, Yutaka Matsuo. [doi]
- Black-box Attacks on Deep Neural Networks via Gradient EstimationArjun Nitin Bhagoji, Warren He, Bo Li 0044, Dawn Song. [doi]