Generalization

Spectral Bias in Practice: The Role of Function Frequency in Generalization NeurIPS 2022 Stability Analysis and Generalization Bounds of Adversarial Training NeurIPS 2022 Stability and Generalization Analysis of Gradient Methods for Shallow Neural Networks NeurIPS 2022 Stability vs Implicit Bias of Gradient Methods on Separable Data and Beyond COLT 2022 Task Discovery: Finding the Tasks that Neural Networks Generalize on NeurIPS 2022 The Implicit Bias of Benign Overfitting COLT 2022 The Missing Invariance Principle found -- the Reciprocal Twin of Invariant Risk Minimization NeurIPS 2022 The Two Dimensions of Worst-Case Training and Their Integrated Effect for Out-of-Domain Generalization CVPR 2022 Understanding Benign Overfitting in Gradient-Based Meta Learning NeurIPS 2022 Uniform Stability for First-Order Empirical Risk Minimization COLT 2022 Universality of empirical risk minimization COLT 2022 Unobserved Local Structures Make Compositional Generalization Hard EMNLP 2022 What is a Good Metric to Study Generalization of Minimax Learners? NeurIPS 2022 What Makes Instruction Learning Hard? An Investigation and a New Challenge in a Synthetic Environment EMNLP 2022 When More Data Hurts: A Troubling Quirk in Developing Broad-Coverage Natural Language Understanding Systems EMNLP 2022 Why neural networks find simple solutions: The many regularizers of geometric complexity NeurIPS 2022 Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power NeurIPS 2022 Analyzing the Generalization Capability of SGLD Using Properties of Gaussian Channels NeurIPS 2021 Anatomy of OntoGUM—Adapting GUM to the OntoNotes Scheme to Evaluate Robustness of SOTA Coreference Algorithms EMNLP 2021 Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation NeurIPS 2021 Benign Overfitting of Constant-Stepsize SGD for Linear Regression COLT 2021 Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning NeurIPS 2021 Convergence Guarantees for Gaussian Process Means With Misspecified Likelihoods and Smoothness JMLR 2021 Ensembling With a Fixed Parameter Budget: When Does It Help and Why? ACML 2021 Fine-grained Generalization Analysis of Inductive Matrix Completion NeurIPS 2021