Top-m identification for linear bandits
This addresses a specific need in drug repurposing by providing the first algorithms for top-m identification in linear bandits, though it is incremental as it builds on existing bandit frameworks.
The paper tackles the problem of identifying the top-m arms with the largest means in a linear bandit model, introducing new algorithms and showing how features can reduce sample complexity, with empirical validation on simulated data and a drug repurposing task.
Motivated by an application to drug repurposing, we propose the first algorithms to tackle the identification of the m $\ge$ 1 arms with largest means in a linear bandit model, in the fixed-confidence setting. These algorithms belong to the generic family of Gap-Index Focused Algorithms (GIFA) that we introduce for Top-m identification in linear bandits. We propose a unified analysis of these algorithms, which shows how the use of features might decrease the sample complexity. We further validate these algorithms empirically on simulated data and on a simple drug repurposing task.