Learning Theory

Transductive Robust Learning Guarantees AISTATS 2022 Transformer Language Models without Positional Encodings Still Learn Positional Information EMNLP 2022 Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models ICLR 2022 Trivial or Impossible --- dichotomous data difficulty masks model differences (on ImageNet and beyond) ICLR 2022 TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learning NeurIPS 2022 Unbiased Math Word Problems Benchmark for Mitigating Solving Bias NAACL 2022 Uncoupled Learning Dynamics with $O(\log T)$ Swap Regret in Multiplayer Games NeurIPS 2022 Under-bagging Nearest Neighbors for Imbalanced Classification JMLR 2022 Understanding and Leveraging Overparameterization in Recursive Value Estimation ICLR 2022 Understanding and Mitigating Data Contamination in Deep Anomaly Detection: A Kernel-based Approach IJCAI 2022 Understanding Benign Overfitting in Gradient-Based Meta Learning NeurIPS 2022 Understanding Contrastive Learning Requires Incorporating Inductive Biases ICML 2022 Understanding Deep Neural Function Approximation in Reinforcement Learning via ε-Greedy Exploration NeurIPS 2022 Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond ICML 2022 Understanding Robust Generalization in Learning Regular Languages ICML 2022 Understanding Stochastic Optimization Behavior at the Layer Update Level (Student Abstract) AAAI 2022 Understanding the Eluder Dimension NeurIPS 2022 Understanding the unstable convergence of gradient descent ICML 2022 Uniform Stability for First-Order Empirical Risk Minimization COLT 2022 Universal and data-adaptive algorithms for model selection in linear contextual bandits ICML 2022 Universality of empirical risk minimization COLT 2022 Universally Consistent Online Learning with Arbitrarily Dependent Responses ALT 2022 Universal Online Learning: an Optimistically Universal Learning Rule COLT 2022 Universal Online Learning with Bounded Loss: Reduction to Binary Classification COLT 2022 Universal Online Learning with Unbounded Losses: Memory Is All You Need ALT 2022