Best-Arm Identification in Linear Bandits

Abstract

We study the best-arm identification problem in linear bandit, where the rewards of the arms depend linearly on an unknown parameter ${\theta }^{\ast }$ and the objective is to return the arm with the largest reward. We characterize the complexity of the problem and introduce sample allocation strategies that pull arms to identify the best arm with a fixed confidence, while minimizing the sample budget. In particular, we show the importance of exploiting the global linear structure to improve the estimate of the reward of near-optimal arms. We analyze the proposed strategies and compare their empirical performance. Finally, as a by-product of our analysis, we point out the connection to the $G$-optimality criterion used in optimal experimental design.

In Advances in Neural Information Processing Systems 27 (NIPS), 2014

Cited by in corpus (12)

• An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits
• Optimal Best-arm Identification in Linear Bandits
• Sequential Experimental Design for Transductive Linear Bandits
• Explicit Best Arm Identification in Linear Bandits Using No-Regret Learners
• Towards Optimal and Efficient Best Arm Identification in Linear Bandits
• Design of Experiments for Stochastic Contextual Linear Bandits
• Sublinear Optimal Policy Value Estimation in Contextual Bandits
• MaxGap Bandit: Adaptive Algorithms for Approximate Ranking
• Refined bounds for randomized experimental design
• Price of Safety in Linear Best Arm Identification
• Online Model Selection: a Rested Bandit Formulation
• A Map of Bandits for E-commerce