Generalization

Optimal Nonlinearities Improve Generalization Performance of Random Features ACML 2023 Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Bounds NeurIPS 2023 Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation CVPR 2023 Sharper Bounds for Uniformly Stable Algorithms with Stationary Mixing Process ICLR 2023 SLOG: A Structural Generalization Benchmark for Semantic Parsing EMNLP 2023 Sparsity-aware generalization theory for deep neural networks COLT 2023 Stability and Generalization of Stochastic Optimization with Nonconvex and Nonsmooth Problems COLT 2023 Stability-Based Generalization Analysis for Mixtures of Pointwise and Pairwise Learning AAAI 2023 Stable Learning via Sparse Variable Independence AAAI 2023 Tackling Combinatorial Distribution Shift: A Matrix Completion Perspective COLT 2023 The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks ICLR 2023 The Memory-Perturbation Equation: Understanding Model's Sensitivity to Data NeurIPS 2023 Toward Better PAC-Bayes Bounds for Uniformly Stable Algorithms NeurIPS 2023 What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models NeurIPS 2023 Which Shortcut Solution Do Question Answering Models Prefer to Learn? AAAI 2023 An Empirical Study of Memorization in NLP ACL 2022 A Non-Asymptotic Moreau Envelope Theory for High-Dimensional Generalized Linear Models NeurIPS 2022 A PAC-Bayesian Generalization Bound for Equivariant Networks NeurIPS 2022 Approximation and Learning with Deep Convolutional Models: a Kernel Perspective ICLR 2022 A Reparametrization-Invariant Sharpness Measure Based on Information Geometry NeurIPS 2022 Assessing Generalization of SGD via Disagreement ICLR 2022 A Theory of PAC Learnability under Transformation Invariances NeurIPS 2022 Benign Overfitting in Two-layer Convolutional Neural Networks NeurIPS 2022 Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules NeurIPS 2022 Chained generalisation bounds COLT 2022