 Mechanic: A Learning Rate TunerNeural Information Processing Systems (NeurIPS), 2023 |
 |
 Unconstrained Dynamic Regret via Sparse CodingNeural Information Processing Systems (NeurIPS), 2023 |
 Scale-free Unconstrained Online Learning for Curved LossesAnnual Conference Computational Learning Theory (COLT), 2022 |
 Parameter-free Online Linear Optimization with Side Information via
Universal Coin BettingInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 |
 PDE-Based Optimal Strategy for Unconstrained Online LearningInternational Conference on Machine Learning (ICML), 2022 |
 Model Selection for Generic Contextual BanditsIEEE Transactions on Information Theory (IEEE Trans. Inf. Theory), 2021 |
 Pareto Optimal Model Selection in Linear BanditsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 |
 Problem-Complexity Adaptive Model Selection for Stochastic Linear
BanditsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2020 |
 Minimax Regret of Switching-Constrained Online Convex Optimization: No
Phase TransitionNeural Information Processing Systems (NeurIPS), 2019 |
 Model selection for contextual banditsNeural Information Processing Systems (NeurIPS), 2019 |
 Lipschitz Adaptivity with Multiple Learning Rates in Online LearningAnnual Conference Computational Learning Theory (COLT), 2019 |
 |
 |
 Tight Lower Bounds for Multiplicative Weights Algorithmic FamiliesInternational Colloquium on Automata, Languages and Programming (ICALP), 2016 |
 |
 |
 Towards Optimal Algorithms for Prediction with Expert AdviceACM-SIAM Symposium on Discrete Algorithms (SODA), 2014 |
 Unconstrained Online Linear Learning in Hilbert Spaces: Minimax
Algorithms and Normal ApproximationsAnnual Conference Computational Learning Theory (COLT), 2014 |
 Towards Minimax Online Learning with Unknown Time HorizonInternational Conference on Machine Learning (ICML), 2013 |
