Top-m identification for linear bandits

2021/03/18 by Réda, Clémence, Kaufmann, Emilie, Delahaye-Duriez, Andrée · 2 citations
#Artificial Intelligence (cs.AI) #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Quantitative Methods (q-bio.QM) #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.2103.10070

Abstract

Motivated by an application to drug repurposing, we propose the first algorithms to tackle the identification of the m ≥ 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.

Cited by

• Challenger-Based Combinatorial Bandits for Subcarrier Selection in OFDM Systems
• Sample Efficient Demonstration Selection for In-Context Learning

Related

• Dealing With Misspecification In Fixed-Confidence Linear Top-m\n Identification
• Best Arm Identification in Generalized Linear Bandits
• Towards Optimal and Efficient Best Arm Identification in Linear Bandits
• Identifying All ε-Best Arms in (Misspecified) Linear Bandits
• Top Two Algorithms Revisited