Online Program

Return to main conference page
Saturday, June 1
Machine Learning
Recent Advances in Statistical Machine Learning and Reinforcement Learning
Sat, Jun 1, 1:00 PM - 2:35 PM
Regency Ballroom AB

Nearly Optimal Adaptive Procedure with Change Detection for Piecewise-Stationary Bandit (305108)

*Zheng Wen, Adobe Research 

Multi-armed bandit (MAB) is a class of online learning problems where a learning agent aims to maximize its expected cumulative reward while repeatedly selecting to pull arms with unknown reward distributions. We consider a scenario where the reward distributions may change in a piecewise-stationary fashion at unknown time steps. We show that by incorporating a simple change-detection component with classic UCB algorithms to detect and adapt to changes, our so-called M-UCB algorithm can achieve nearly optimal regret bound on the order of $O(\sqrt{MKT\log T})$, where $T$ is the number of time steps, $K$ is the number of arms, and $M$ is the number of stationary segments. Comparison with the best available lower bound shows that our M-UCB is nearly optimal in $T$ up to a logarithmic factor. We also compare M-UCB with the state-of-the-art algorithms in numerical experiments using a public Yahoo! dataset and a proprietary real-world digital marketing dataset to demonstrate its superior performance.