Learning Theory

Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers NeurIPS 2021 Minimax Regret for Stochastic Shortest Path NeurIPS 2021 Minimax sample complexity for turn-based stochastic game UAI 2021 Misspecification in Prediction Problems and Robustness via Improper Learning AISTATS 2021 Misspecified Gaussian Process Bandit Optimization NeurIPS 2021 Mixture Martingales Revisited with Applications to Sequential Tests and Confidence Intervals JMLR 2021 Model-Free Online Learning in Unknown Sequential Decision Making Problems and Games AAAI 2021 Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity ICML 2021 Modeling Risky Choices in Unknown Environments ACML 2021 Model Performance Scaling with Multiple Data Sources ICML 2021 Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model NeurIPS 2021 Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment ICML 2021 Multi-armed Bandit Requiring Monotone Arm Sequences NeurIPS 2021 Multi-Armed Bandits with Bounded Arm-Memory: Near-Optimal Guarantees for Best-Arm Identification and Regret Minimization NeurIPS 2021 Multiclass Boosting and the Cost of Weak Learning NeurIPS 2021 Multiclass versus Binary Differentially Private PAC Learning NeurIPS 2021 Multi-group Agnostic PAC Learnability ICML 2021 Multinomial Logit Contextual Bandits: Provable Optimality and Practicality AAAI 2021 Multiple Descent: Design Your Own Generalization Curve NeurIPS 2021 Multitask Bandit Learning Through Heterogeneous Feedback Aggregation AISTATS 2021 Narrow Margins: Classification, Margins and Fat Tails ICML 2021 Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs NeurIPS 2021 Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes COLT 2021 Near-Optimal Model-Free Reinforcement Learning in Non-Stationary Episodic MDPs ICML 2021 Near-Optimal No-Regret Learning in General Games NeurIPS 2021