Theory

A Geometric Analysis of Neural Collapse with Unconstrained Features NeurIPS 2021 A Gradient Flow Framework For Analyzing Network Pruning ICLR 2021 A Ladder of Causal Distances IJCAI 2021 A Law of Iterated Logarithm for Multi-Agent Reinforcement Learning NeurIPS 2021 A Law of Robustness for Two-Layers Neural Networks COLT 2021 All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality EMNLP 2021 Almost Envy-Freeness for Groups: Improved Bounds via Discrepancy Theory IJCAI 2021 Almost sure convergence rates for Stochastic Gradient Descent and Stochastic Heavy Ball COLT 2021 A Method for Taxonomy-Aware Embeddings Evaluation (Student Abstract) AAAI 2021 A Multivariate Complexity Analysis of the Material Consumption Scheduling Problem AAAI 2021 Analysis of one-hidden-layer neural networks via the resolvent method NeurIPS 2021 Analytic Insights into Structure and Rank of Neural Network Hessian Maps NeurIPS 2021 Analytic Study of Families of Spurious Minima in Two-Layer ReLU Neural Networks: A Tale of Symmetry II NeurIPS 2021 Analyzing the discrepancy principle for kernelized spectral filter learning algorithms JMLR 2021 Analyzing the tree-layer structure of Deep Forests ICML 2021 An Analysis of Approval-Based Committee Rules for 2D-Euclidean Elections AAAI 2021 An Empirical Study on Neural Keyphrase Generation NAACL 2021 An Exponential Lower Bound for Linearly Realizable MDP with Constant Suboptimality Gap NeurIPS 2021 An Information-Geometric Distance on the Space of Tasks ICML 2021 A No-go Theorem for Robust Acceleration in the Hyperbolic Plane NeurIPS 2021 A Non-Linear Structural Probe NAACL 2021 A nonparametric method for gradual change problems with statistical guarantees NeurIPS 2021 An optimization and generalization analysis for max-pooling networks UAI 2021 A Nullspace Property for Subspace-Preserving Recovery ICML 2021 Approximate optimization of convex functions with outlier noise NeurIPS 2021