Generalization

Remember What You Want to Forget: Algorithms for Machine Unlearning NeurIPS 2021 Sequence Length is a Domain: Length-based Overfitting in Transformer Models EMNLP 2021 SGD Generalizes Better Than GD (And Regularization Doesn’t Help) COLT 2021 Shape Matters: Understanding the Implicit Bias of the Noise Covariance COLT 2021 Sharper Generalization Bounds for Learning with Gradient-dominated Objective Functions ICLR 2021 Stability and Generalization of Decentralized Stochastic Gradient Descent AAAI 2021 Systematic Generalization on gSCAN: What is Nearly Solved and What is Next? EMNLP 2021 The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers EMNLP 2021 Towards Sharper Generalization Bounds for Structured Prediction NeurIPS 2021 User-Level Differentially Private Learning via Correlated Sampling NeurIPS 2021 Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization ICML 2021 Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability NeurIPS 2021 A Closer Look at the Training Strategy for Modern Meta-Learning NeurIPS 2020 An Unbiased Risk Estimator for Learning with Augmented Classes NeurIPS 2020 A One-step Approach to Covariate Shift Adaptation ACML 2020 A Statistical Mechanics Framework for Task-Agnostic Sample Design in Machine Learning NeurIPS 2020 BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance EMNLP 2020 COGS: A Compositional Generalization Challenge Based on Semantic Interpretation EMNLP 2020 Computing the Testing Error Without a Testing Set CVPR 2020 Conditioning and Processing: Techniques to Improve Information-Theoretic Generalization Bounds NeurIPS 2020 Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics EMNLP 2020 Decision trees as partitioning machines to characterize their generalization properties NeurIPS 2020 Ensembles of Locally Independent Prediction Models AAAI 2020 Feature Variance Regularization: A Simple Way to Improve the Generalizability of Neural Networks AAAI 2020 Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics NeurIPS 2020