Learning Theory

On the Connection between Pre-training Data Diversity and Fine-tuning Robustness NeurIPS 2023 On the Consistency Rate of Decision Tree Learning Algorithms AISTATS 2023 On the Convergence and Sample Complexity Analysis of Deep Q-Networks with ε-Greedy Exploration NeurIPS 2023 On the Convergence of CART under Sufficient Impurity Decrease Condition NeurIPS 2023 On the Convergence of Encoder-only Shallow Transformers NeurIPS 2023 On the convergence of the MLE as an estimator of the learning rate in the Exp3 algorithm ICML 2023 On the Existence of a Complexity in Fixed Budget Bandit Identification COLT 2023 On the Generalization Ability of Retrieval-Enhanced Transformers EACL 2023 On the Generalization Error of Stochastic Mirror Descent for Quadratically-Bounded Losses: an Improved Analysis NeurIPS 2023 On the Generalization Properties of Diffusion Models NeurIPS 2023 On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network Parametrization ICML 2023 On the Implicit Bias of Linear Equivariant Steerable Networks NeurIPS 2023 On the Importance of Feature Separability in Predicting Out-Of-Distribution Error NeurIPS 2023 On the Intersection of Context-Free and Regular Languages EACL 2023 On the Learnability of Multilabel Ranking NeurIPS 2023 On the limitations of Markovian rewards to express multi-objective, risk-sensitive, and modal tasks UAI 2023 On the Lower Bound of Minimizing Polyak-Łojasiewicz functions COLT 2023 On the Minimax Regret for Online Learning with Feedback Graphs NeurIPS 2023 On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness ICML 2023 On the Representational Capacity of Recurrent Neural Language Models EMNLP 2023 On the Robustness of Randomized Ensembles to Adversarial Perturbations ICML 2023 On the Role of Attention in Prompt-tuning ICML 2023 On the Role of Entanglement and Statistics in Learning NeurIPS 2023 On the Role of Generalization in Transferability of Adversarial Examples UAI 2023 On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences NeurIPS 2023