conftrace_

quadratic variation

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

regret bound (5) online learning (4) multi-armed bandit (3) variation-bounded regret (1) label efficient prediction (1) follow the leader (1) linear time algorithm (1) adversarial bandit (1) switching cost (1) martingale method (1)

Papers

Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds COLT 2023 Policy Evaluation and Temporal-Difference Learning in Continuous Time and Space: A Martingale Approach JMLR 2022 On Adaptivity in Information-Constrained Online Learning AAAI 2020 Refined Lower Bounds for Adversarial Bandits NeurIPS 2016 Higher-Order Regret Bounds with Switching Costs COLT 2014 A simple multi-armed bandit algorithm with optimal variation-bounded regret COLT 2011