Learning Theory

Tensor Regression Meets Gaussian Processes AISTATS 2018 Testing for Families of Distributions via the Fourier Transform NeurIPS 2018 The committee machine: Computational to statistical gaps in learning a two-layers neural network NeurIPS 2018 The Description Length of Deep Learning models NeurIPS 2018 The Dynamics of Learning: A Random Matrix Approach ICML 2018 The Fine Line between Linguistic Generalization and Failure in Seq2Seq-Attention Models NAACL 2018 The Generalization Error of Dictionary Learning with Moreau Envelopes ICML 2018 The Implicit Bias of Gradient Descent on Separable Data ICLR 2018 The Implicit Bias of Gradient Descent on Separable Data JMLR 2018 The Limits of Maxing, Ranking, and Preference Learning ICML 2018 The Pessimistic Limits and Possibilities of Margin-based Losses in Semi-supervised Learning NeurIPS 2018 The power of deeper networks for expressing natural functions ICLR 2018 The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning ICML 2018 Tight Bounds for Collaborative PAC Learning via Multiplicative Weights NeurIPS 2018 Tight Regret Bounds for Bayesian Optimization in One Dimension ICML 2018 Time-Space Tradeoffs for Learning Finite Functions from Random Evaluations, with Applications to Polynomials COLT 2018 To Understand Deep Learning We Need to Understand Kernel Learning ICML 2018 Towards Black-box Iterative Machine Teaching ICML 2018 Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation NeurIPS 2018 Unbiased Learning-to-Rank with Biased Feedback IJCAI 2018 Understanding Deep Neural Networks with Rectified Linear Units ICLR 2018 Understanding Generalization and Optimization Performance of Deep CNNs ICML 2018 Understanding Weight Normalized Deep Neural Networks with Rectified Linear Units NeurIPS 2018 Uniform Convergence of Gradients for Non-Convex Learning and Optimization NeurIPS 2018 Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning ICML 2018