Theory

Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning AISTATS 2020 Asymptotically Optimal Exact Minibatch Metropolis-Hastings NeurIPS 2020 Asymptotic Analysis of Sampling Estimators for Randomized Numerical Linear Algebra Algorithms AISTATS 2020 Asymptotic Analysis via Stochastic Differential Equations of Gradient Descent Algorithms in Statistical and Computational Paradigms JMLR 2020 Asymptotic Guarantees for Generative Modeling Based on the Smooth Wasserstein Distance NeurIPS 2020 A Tale of Two-Timescale Reinforcement Learning with the Tightest Finite-Time Bound AAAI 2020 A Theoretical Framework for Target Propagation NeurIPS 2020 A Three Sample Hypothesis Test for Evaluating Generative Models AISTATS 2020 A Topology Layer for Machine Learning AISTATS 2020 Attribute Noise Robust Binary Classification (Student Abstract) AAAI 2020 Attribution in Scale and Space CVPR 2020 A Unified Switching System Perspective and Convergence Analysis of Q-Learning Algorithms NeurIPS 2020 A Unifying Theory of Transition-based and Sequence Labeling Parsing COLING 2020 A Universal Approximation Theorem of Deep Neural Networks for Expressing Probability Distributions NeurIPS 2020 Automated Spectral Kernel Learning AAAI 2020 Automatic Detection of Machine Generated Text: A Critical Survey COLING 2020 Batch normalization provably avoids ranks collapse for randomly initialised deep networks NeurIPS 2020 BattleNet: Capturing Advantageous Battlefield in RTS Games (Student Abstract) AAAI 2020 Bayesian Deep Learning and a Probabilistic Perspective of Generalization NeurIPS 2020 Benchmarking Adversarial Robustness on Image Classification CVPR 2020 Benchmarking Deep Inverse Models over time, and the Neural-Adjoint method NeurIPS 2020 Beyond exploding and vanishing gradients: analysing RNN training using attractors and smoothness AISTATS 2020 Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks ICLR 2020 Beyond Pairwise Comparisons in Social Choice: A Setwise Kemeny Aggregation Problem AAAI 2020 Bounded Incentives in Manipulating the Probabilistic Serial Rule AAAI 2020