Theory

Representation Learning Beyond Linear Prediction Functions NeurIPS 2021 Representer Point Selection via Local Jacobian Expansion for Post-hoc Classifier Explanation of Deep Neural Networks and Ensemble Models NeurIPS 2021 Representer Theorems in Banach Spaces: Minimum Norm Interpolation, Regularized Learning and Semi-Discrete Inverse Problems JMLR 2021 ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees NeurIPS 2021 Responsibility Attribution in Parameterized Markovian Models AAAI 2021 Revealing the Structure of Deep Neural Networks via Convex Duality ICML 2021 Revisiting Model Stitching to Compare Neural Representations NeurIPS 2021 Revisiting the Calibration of Modern Neural Networks NeurIPS 2021 Revisiting Weight Initialization of Deep Neural Networks ACML 2021 Reward is enough for convex MDPs NeurIPS 2021 Right for Better Reasons: Training Differentiable Models by Constraining their Influence Functions AAAI 2021 Ringing ReLUs: Harmonic Distortion Analysis of Nonlinear Feedforward Networks ICLR 2021 Risk Bounds and Calibration for a Smart Predict-then-Optimize Method NeurIPS 2021 Risk Monotonicity in Statistical Learning NeurIPS 2021 RL for Latent MDPs: Regret Guarantees and a Lower Bound NeurIPS 2021 Robust Implicit Networks via Non-Euclidean Contractions NeurIPS 2021 Robust Mean Estimation on Highly Incomplete Data with Arbitrary Outliers AISTATS 2021 Robustness Guarantees for Mode Estimation with an Application to Bandits AAAI 2021 Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels AAAI 2021 Safe Reinforcement Learning by Imagining the Near Future NeurIPS 2021 Sample Complexity Bounds for Two Timescale Value-based Reinforcement Learning Algorithms AISTATS 2021 Sample Complexity of Policy Gradient Finding Second-Order Stationary Points AAAI 2021 Sample Complexity of Robust Linear Classification on Separated Data ICML 2021 Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity ICML 2021 Satisfiability and Algorithms for Non-uniform Random k-SAT AAAI 2021