The Role of Contextual Information in Best Arm Identification
arXiv:2106.14077
Abstract
We study the best-arm identification problem with fixed confidence when contextual (covariate) information is available in stochastic bandits. Although we can use contextual information in each round, we are interested in the marginalized mean reward over the contextual distribution. Our goal is to identify the best arm with a minimal number of samplings under a given value of the error rate. We show the instance-specific sample complexity lower bounds for the problem. Then, we propose a context-aware version of the "Track-and-Stop" strategy, wherein the proportion of the arm draws tracks the set of optimal allocations and prove that the expected number of arm draws matches the lower bound asymptotically. We demonstrate that contextual information can be used to improve the efficiency of the identification of the best marginalized mean reward compared with the results of Garivier & Kaufmann (2016). We experimentally confirm that context information contributes to faster best-arm identification.
References in corpus (9)
- On the Complexity of Best Arm Identification in Multi-Armed Bandit Models
- Unbiased Offline Evaluation of Contextual-bandit-based News Article Recommendation Algorithms
- lil' UCB : An Optimal Exploration Algorithm for Multi-Armed Bandits
- Optimal Best Arm Identification with Fixed Confidence
- Best-Arm Identification in Linear Bandits
- RELEAF: An Algorithm for Learning and Exploiting Relevance
- Simple Regret Minimization for Contextual Bandits
- The Econometrics of Randomized Experiments
- A/B/n Testing with Control in the Presence of Subpopulations