Learning Theory

How Many Representatives Do We Need? The Optimal Size of a Congress Voting on Binary Issues AAAI 2022 How Much More Data Do I Need? Estimating Requirements for Downstream Tasks CVPR 2022 How Powerful are K-hop Message Passing Graph Neural Networks NeurIPS 2022 How to Learn when Data Gradually Reacts to Your Model AISTATS 2022 How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis ICLR 2022 Identifiability Conditions for Domain Adaptation ICML 2022 Identifiable Energy-based Representations: An Application to Estimating Heterogeneous Causal Effects AISTATS 2022 Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials NeurIPS 2022 IMED-RL: Regret optimal learning of ergodic Markov decision processes NeurIPS 2022 Implicit Bias of Linear Equivariant Networks ICML 2022 Implicit Bias of the Step Size in Linear Diagonal Neural Networks ICML 2022 Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions NeurIPS 2022 Implicit Regularization with Polynomial Growth in Deep Tensor Factorization ICML 2022 Improved Algorithms for Misspecified Linear Markov Decision Processes AISTATS 2022 Improved Algorithms for Neural Active Learning NeurIPS 2022 Improved Bounds on Neural Complexity for Representing Piecewise Linear Functions NeurIPS 2022 Improved Fine-Tuning by Better Leveraging Pre-Training Data NeurIPS 2022 Improved Generalization Bounds for Adversarially Robust Learning JMLR 2022 Improved Pure Exploration in Linear Bandits with No-Regret Learning IJCAI 2022 Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging EMNLP 2022 Incentivizing Combinatorial Bandit Exploration NeurIPS 2022 Independence Testing for Bounded Degree Bayesian Networks NeurIPS 2022 Inductive Biases and Variable Creation in Self-Attention Mechanisms ICML 2022 Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality NeurIPS 2022 Information Discrepancy in Strategic Learning ICML 2022