Fixed-Budget Best-Arm Identification in Structured Bandits
This addresses the limitation of prior unstructured methods for researchers and practitioners in bandit problems, offering a domain-specific incremental improvement.
The paper tackles the problem of best-arm identification in structured bandits with a fixed budget, proposing a tractable algorithm that uses joint generalization models and G-optimal design to eliminate suboptimal arms, achieving competitive error guarantees in linear models and being the first practical analyzed method for generalized linear models.
Best-arm identification (BAI) in a fixed-budget setting is a bandit problem where the learning agent maximizes the probability of identifying the optimal (best) arm after a fixed number of observations. Most works on this topic study unstructured problems with a small number of arms, which limits their applicability. We propose a general tractable algorithm that incorporates the structure, by successively eliminating suboptimal arms based on their mean reward estimates from a joint generalization model. We analyze our algorithm in linear and generalized linear models (GLMs), and propose a practical implementation based on a G-optimal design. In linear models, our algorithm has competitive error guarantees to prior works and performs at least as well empirically. In GLMs, this is the first practical algorithm with analysis for fixed-budget BAI.