Theory

On Focal Loss for Class-Posterior Probability Estimation: A Theoretical Perspective CVPR 2021 On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learning AAAI 2021 On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness NeurIPS 2021 On Linear Identifiability of Learned Representations ICML 2021 On Linear Stability of SGD and Input-Smoothness of Neural Networks NeurIPS 2021 Online Facility Location with Multiple Advice NeurIPS 2021 On Lower Bounds for Standard and Robust Gaussian Process Bandit Optimization ICML 2021 On Online Optimization: Dynamic Regret Analysis of Strongly Convex and Smooth Problems AAAI 2021 On Path Integration of Grid Cells: Group Representation and Isotropic Scaling NeurIPS 2021 On Provable Benefits of Depth in Training Graph Convolutional Networks NeurIPS 2021 On random kernels of residual architectures UAI 2021 On Robustness of Neural Semantic Parsers EACL 2021 On Robust Optimal Transport: Computational Complexity and Barycenter Computation NeurIPS 2021 On Sampled Metrics for Item Recommendation (Extended Abstract) IJCAI 2021 On the Algorithmic Stability of Adversarial Training NeurIPS 2021 On the Bias-Variance-Cost Tradeoff of Stochastic Optimization NeurIPS 2021 On the Complexity of Finding Justifications for Collective Decisions AAAI 2021 On the Consistency of Metric and Non-Metric K-Medoids AISTATS 2021 On the Convergence of Langevin Monte Carlo: The Interplay between Tail Growth and Smoothness COLT 2021 On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning NeurIPS 2021 On the Cryptographic Hardness of Learning Single Periodic Neurons NeurIPS 2021 On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization Analysis ICLR 2021 On the distributional properties of adaptive gradients UAI 2021 On the Equivalence between Neural Network and Support Vector Machine NeurIPS 2021 On the Estimation Bias in Double Q-Learning NeurIPS 2021