Theory

On the Existence of The Adversarial Bayes Classifier NeurIPS 2021 On the Explicit Role of Initialization on the Convergence and Implicit Bias of Overparametrized Linear Networks ICML 2021 On the Expressivity of Markov Reward NeurIPS 2021 On the Hardness of Robust Classification JMLR 2021 On the Inherent Regularization Effects of Noise Injection During Training ICML 2021 On the interplay between data structure and loss function in classification problems NeurIPS 2021 On the Intrinsic Differential Privacy of Bagging IJCAI 2021 On the Limits of Minimal Pairs in Contrastive Evaluation EMNLP 2021 On the mapping between Hopfield networks and Restricted Boltzmann Machines ICLR 2021 On the Memory Mechanism of Tensor-Power Recurrent Models AISTATS 2021 On the Optimal Efficiency of A* with Dominance Pruning AAAI 2021 On the Optimality of Kernel-Embedding Based Goodness-of-Fit Tests JMLR 2021 On the Power of Differentiable Learning versus PAC and SQ Learning NeurIPS 2021 On the Power of Edge Independent Graph Models NeurIPS 2021 On the Problem of Underranking in Group-Fair Ranking ICML 2021 On the Random Conjugate Kernel and Neural Tangent Kernel ICML 2021 On the Second-order Convergence Properties of Random Search Methods NeurIPS 2021 On the Softmax Bottleneck of Recurrent Language Models AAAI 2021 On the Stability Properties and the Optimization Landscape of Training Problems with Squared Loss for Neural Networks and General Nonlinear Conic Approximation Schemes JMLR 2021 On the Stochastic Stability of Deep Markov Models NeurIPS 2021 On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift JMLR 2021 On the Tractability of SHAP Explanations AAAI 2021 On the Universality of Graph Neural Networks on Large Random Graphs NeurIPS 2021 On the Universality of Rotation Equivariant Point Cloud Networks ICLR 2021 On the Variance of the Fisher Information for Deep Learning NeurIPS 2021