Table of Contents

• Conference on Learning Theory 2016: PrefaceVitaly Feldman, Alexander Rakhlin. 1-3 [doi]
• An efficient algorithm for contextual bandits with knapsacks, and an extension to concave objectivesShipra Agrawal, Nikhil R. Devanur, Lihong Li. 4-18 [doi]
• Learning and Testing Junta DistributionsMaryam Aliakbarpour, Eric Blais, Ronitt Rubinfeld. 19-46 [doi]
• Sign rank versus VC dimensionNoga Alon, Shay Moran, Amir Yehudayoff. 47-80 [doi]
• Efficient approaches for escaping higher order saddle points in non-convex optimizationAnimashree Anandkumar, Rong Ge. 81-102 [doi]
• Monte Carlo Markov Chain Algorithms for Sampling Strongly Rayleigh Distributions and Determinantal Point ProcessesNima Anari, Shayan Oveis Gharan, Alireza Rezaei. 103-115 [doi]
• An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial banditsPeter Auer, Chao-Kai Chiang. 116-120 [doi]
• Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear ModelsBernardo Ávila Pires. 121-151 [doi]
• Learning and 1-bit Compressed Sensing under Asymmetric NoisePranjal Awasthi, Maria-Florina Balcan, Nika Haghtalab, Hongyang Zhang. 152-192 [doi]
• Reinforcement Learning of POMDPs using Spectral MethodsKamyar Azizzadenesheli, Alessandro Lazaric, Animashree Anandkumar. 193-256 [doi]
• Highly-Smooth Zero-th Order Online OptimizationFrancis R. Bach, Vianney Perchet. 257-283 [doi]
• An Improved Gap-Dependency Analysis of the Noisy Power MethodMaria-Florina Balcan, Simon Shaolei Du, Yining Wang, Adams Wei Yu. 284-309 [doi]
• Learning Combinatorial Functions from Pairwise ComparisonsMaria-Florina Balcan, Ellen Vitercik, Colin White. 310-335 [doi]
• Instance-dependent Regret Bounds for Dueling BanditsAkshay Balsubramani, Zohar S. Karnin, Robert E. Schapire, Masrour Zoghi. 336-360 [doi]
• On the low-rank approach for semidefinite programs arising in synchronization and community detectionAfonso S. Bandeira, Nicolas Boumal, Vladislav Voroninski. 361-382 [doi]
• Information-theoretic thresholds for community detection in sparse networksJess Banks, Cristopher Moore, Joe Neeman, Praneeth Netrapalli. 383-416 [doi]
• Noisy Tensor Completion via the Sum-of-Squares HierarchyBoaz Barak, Ankur Moitra. 417-445 [doi]
• Basis Learning as an Algorithmic PrimitiveMikhail Belkin, Luis Rademacher, James R. Voss. 446-487 [doi]
• Aggregation of supports along the Lasso pathPierre C. Bellec. 488-529 [doi]
• Dropping Convexity for Faster Semi-definite OptimizationSrinadh Bhojanapalli, Anastasios Kyrillidis, Sujay Sanghavi. 530-582 [doi]
• Multi-scale exploration of convex functions and bandit convex optimizationSébastien Bubeck, Ronen Eldan. 583-589 [doi]
• Tight (Lower) Bounds for the Fixed Budget Best Arm Identification Bandit ProblemAlexandra Carpentier, Andrea Locatelli. 590-604 [doi]
• Delay and Cooperation in Nonstochastic BanditsNicolò Cesa-Bianchi, Claudio Gentile, Yishay Mansour, Alberto Minora. 605-622 [doi]
• On the Approximability of Sparse PCASiu On Chan, Dimitris Papailliopoulos, Aviad Rubinstein. 623-646 [doi]
• Pure Exploration of Multi-armed Bandit Under Matroid ConstraintsLijie Chen, Anupam Gupta, Jian Li. 647-669 [doi]
• Provably manipulation-resistant reputation systemsPaul Christiano. 670-697 [doi]
• On the Expressive Power of Deep Learning: A Tensor AnalysisNadav Cohen, Or Sharir, Amnon Shashua. 698-728 [doi]
• A Light Touch for Heavily Constrained SGDAndrew Cotter, Maya R. Gupta, Jan Pfeifer. 729-771 [doi]
• Adaptive Learning with Robust Generalization GuaranteesRachel Cummings, Katrina Ligett, Kobbi Nissim, Aaron Roth, Zhiwei Steven Wu. 772-814 [doi]
• Complexity Theoretic Limitations on Learning DNF'sAmit Daniely, Shai Shalev-Shwartz. 815-830 [doi]
• Optimal Learning via the Fourier Transform for Sums of Independent Integer Random VariablesIlias Diakonikolas, Daniel M. Kane, Alistair Stewart. 831-849 [doi]
• Properly Learning Poisson Binomial Distributions in Almost Polynomial TimeIlias Diakonikolas, Daniel M. Kane, Alistair Stewart. 850-878 [doi]
• Asymptotic behavior of \(\ell_p\)-based Laplacian regularization in semi-supervised learningAhmed El Alaoui. 879-906 [doi]
• The Power of Depth for Feedforward Neural NetworksRonen Eldan, Ohad Shamir. 907-940 [doi]
• Online Learning and Blackwell Approachability in Quitting GamesJános Flesch, Rida Laraki, Vianney Perchet. 941-942 [doi]
• Spectral thresholds in the bipartite stochastic block modelLaura Florescu, Will Perkins. 943-959 [doi]
• Online Sparse Linear RegressionDean P. Foster, Satyen Kale, Howard J. Karloff. 960-970 [doi]
• Preference-based TeachingZiyuan Gao, Christoph Ries, Hans-Ulrich Simon, Sandra Zilles. 971-997 [doi]
• Optimal Best Arm Identification with Fixed ConfidenceAurélien Garivier, Emilie Kaufmann. 998-1027 [doi]
• Maximin Action Identification: A New Bandit Framework for GamesAurélien Garivier, Emilie Kaufmann, Wouter M. Koolen. 1028-1050 [doi]
• Semidefinite Programs for Exact Recovery of a Hidden CommunityBruce E. Hajek, Yihong Wu, Jiaming Xu. 1051-1095 [doi]
• Online Learning with Low Rank ExpertsElad Hazan, Tomer Koren, Roi Livni, Yishay Mansour. 1096-1114 [doi]
• Optimal rates for total variation denoisingJan-Christian Hü. 1115-1146 [doi]
• Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja's AlgorithmPrateek Jain 0002, Chi Jin, Sham M. Kakade, Praneeth Netrapalli, Aaron Sidford. 1147-1164 [doi]
• Online Isotonic RegressionWojciech Kotlowski. 1165-1189 [doi]
• Time series prediction and online learningVitaly Kuznetsov, Mehryar Mohri. 1190-1213 [doi]
• Regret Analysis of the Finite-Horizon Gittins Index Strategy for Multi-Armed BanditsTor Lattimore. 1214-1245 [doi]
• Gradient Descent Only Converges to MinimizersJason D. Lee, Max Simchowitz, Michael I. Jordan, Benjamin Recht. 1246-1257 [doi]
• Learning Communities in the Presence of ErrorsKonstantin Makarychev, Yury Makarychev, Aravindan Vijayaraghavan. 1258-1291 [doi]
• On the capacity of information processing systemsLaurent Massoulié, Kuang Xu. 1292-1297 [doi]
• Learning Simple AuctionsJamie Morgenstern, Tim Roughgarden. 1298-1318 [doi]
• Density Evolution in the Degree-correlated Stochastic Block ModelElchanan Mossel, Jiaming Xu. 1319-1356 [doi]
• Cortical Computation via Iterative ConstructionsChristos H. Papadimitriou, Samantha Petti, Santosh Vempala. 1357-1375 [doi]
• When can we rank well from comparisons of \(O(n\log(n))\) non-actively chosen pairs?Arun Rajkumar, Shivani Agarwal 0001. 1376-1401 [doi]
• How to calculate partition functions using convex programming hierarchies: provable bounds for variational methodsAndrej Risteski. 1402-1416 [doi]
• Simple Bayesian Algorithms for Best Arm IdentificationDaniel Russo. 1417-1418 [doi]
• Interactive Algorithms: from Pool to StreamSivan Sabato, Tom Hess. 1419-1439 [doi]
• Best-of-K-banditsMax Simchowitz, Kevin G. Jamieson, Benjamin Recht. 1440-1489 [doi]
• Memory, Communication, and Statistical QueriesJacob Steinhardt, Gregory Valiant, Stefan Wager. 1490-1516 [doi]
• benefits of depth in neural networksMatus Telgarsky. 1517-1539 [doi]
• A Guide to Learning Arithmetic CircuitsIlya Volkovich. 1540-1561 [doi]
• Online learning in repeated auctionsJonathan Weed, Vianney Perchet, Philippe Rigollet. 1562-1583 [doi]
• The Extended Littlestone's Dimension for Learning with Mistakes and AbstentionsChicheng Zhang, Kamalika Chaudhuri. 1584-1616 [doi]
• First-order Methods for Geodesically Convex OptimizationHongyi Zhang, Suvrit Sra. 1617-1638 [doi]
• Open Problem: Approximate Planning of POMDPs in the class of Memoryless PoliciesKamyar Azizzadenesheli, Alessandro Lazaric, Animashree Anandkumar. 1639-1642 [doi]
• Open Problem: Best Arm Identification: Almost Instance-Wise Optimality and the Gap Entropy ConjectureLijie Chen, Jian Li. 1643-1646 [doi]
• Open Problem: Kernel methods on manifolds and metric spaces. What is the probability of a positive definite geodesic exponential kernel?Aasa Feragen, Søren Hauberg. 1647-1650 [doi]
• Open Problem: Second order regret bounds based on scaling timeYoav Freund. 1651-1654 [doi]
• Open Problem: Property Elicitation and Elicitation ComplexityRafael M. Frongillo, Ian A. Kash, Stephen Becker. 1655-1658 [doi]
• Open Problem: Parameter-Free and Scale-Free Online AlgorithmsFrancesco Orabona, Dávid Pál. 1659-1664 [doi]