Title |
|---|
 Second Order Path Variationals in Non-Stationary Online LearningInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 |
 Smoothed Online Convex Optimization Based on Discounted-Normal-PredictorNeural Information Processing Systems (NeurIPS), 2022 |
 |
 Spatially Adaptive Online Prediction of Piecewise Regular FunctionsInternational Conference on Algorithmic Learning Theory (ALT), 2022 |
 Parameter-free Mirror DescentAnnual Conference Computational Learning Theory (COLT), 2022 |
 Online Control of Unknown Time-Varying Dynamical SystemsNeural Information Processing Systems (NeurIPS), 2022 |
 Damped Online Newton Step for Portfolio SelectionAnnual Conference Computational Learning Theory (COLT), 2022 |
 Corralling a Larger Band of Bandits: A Case Study on Switching Regret
for Linear BanditsAnnual Conference Computational Learning Theory (COLT), 2022 |
 New Projection-free Algorithms for Online Convex Optimization with
Adaptive Regret GuaranteesAnnual Conference Computational Learning Theory (COLT), 2022 |
 Optimal Dynamic Regret in Proper Online Learning with Strongly Convex
Losses and BeyondInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 |
 Learning to Price Against a Moving TargetInternational Conference on Machine Learning (ICML), 2021 |
 Beyond Bandit Feedback in Online Multiclass ClassificationNeural Information Processing Systems (NeurIPS), 2021 |
 Optimal Dynamic Regret in Exp-Concave Online LearningAnnual Conference Computational Learning Theory (COLT), 2021 |
 A Simple Approach for Non-stationary Linear BanditsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2020 |
 Non-stationary Reinforcement Learning without Prior Knowledge: An
Optimal Black-box ApproachAnnual Conference Computational Learning Theory (COLT), 2021 |
 Non-stationary Online Learning with Memory and Non-stochastic ControlInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 |
 Adversarial Tracking Control via Strongly Adaptive Online Learning with
MemoryInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 |
 Impossible Tuning Made Possible: A New Expert Algorithm and Its
ApplicationsAnnual Conference Computational Learning Theory (COLT), 2021 |
 An Optimal Reduction of TV-Denoising to Adaptive Online LearningInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 |
 Adaptive Online Estimation of Piecewise Polynomial TrendsNeural Information Processing Systems (NeurIPS), 2020 |
 Comparator-adaptive Convex BanditsNeural Information Processing Systems (NeurIPS), 2020 |
 Adaptive Regret for Control of Time-Varying DynamicsConference on Learning for Dynamics & Control (L4DC), 2020 |
 Taking a hint: How to leverage loss predictors in contextual bandits?Annual Conference Computational Learning Theory (COLT), 2020 |
 Beyond UCB: Optimal and Efficient Contextual Bandits with Regression
OraclesInternational Conference on Machine Learning (ICML), 2020 |
 Minimizing Dynamic Regret and Adaptive Regret SimultaneouslyInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2020 |
 Dynamic Local Regret for Non-convex Online ForecastingNeural Information Processing Systems (NeurIPS), 2019 |
 Bandit Convex Optimization in Non-stationary EnvironmentsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2019 |
 The Adversarial Robustness of SamplingIACR Cryptology ePrint Archive (IACR ePrint), 2019 |
 Dual Adaptivity: A Universal Algorithm for Minimizing the Adaptive
Regret of Convex FunctionsNeural Information Processing Systems (NeurIPS), 2019 |
 Online Forecasting of Total-Variation-bounded SequencesNeural Information Processing Systems (NeurIPS), 2019 |
 Equipping Experts/Bandits with Long-term MemoryNeural Information Processing Systems (NeurIPS), 2019 |
 Adaptivity and Optimality: A Universal Algorithm for Online Convex
OptimizationConference on Uncertainty in Artificial Intelligence (UAI), 2019 |
