DeepAI AI Chat
Log In Sign Up

Optimal Best-arm Identification in Linear Bandits

by   Yassir Jedra, et al.

We study the problem of best-arm identification with fixed confidence in stochastic linear bandits. The objective is to identify the best arm with a given level of certainty while minimizing the sampling budget. We devise a simple algorithm whose sampling complexity matches known instance-specific lower bounds, asymptotically almost surely and in expectation. The algorithm relies on an arm sampling rule that tracks an optimal proportion of arm draws, and that remarkably can be updated as rarely as we wish, without compromising its theoretical guarantees. Moreover, unlike existing best-arm identification strategies, our algorithm uses a stopping rule that does not depend on the number of arms. Experimental results suggest that our algorithm significantly outperforms existing algorithms. The paper further provides a first analysis of the best-arm identification problem in linear bandits with a continuous set of arms.


page 1

page 2

page 3

page 4


Towards Minimax Optimal Best Arm Identification in Linear Bandits

We study the problem of best arm identification in linear bandits in the...

Best Arm Identification in Generalized Linear Bandits

Motivated by drug design, we consider the best-arm identification proble...

Measurement-based Admission Control in Sliced Networks: A Best Arm Identification Approach

In sliced networks, the shared tenancy of slices requires adaptive admis...

Selective Sampling for Online Best-arm Identification

This work considers the problem of selective-sampling for best-arm ident...

Towards Optimal and Efficient Best Arm Identification in Linear Bandits

We give a new algorithm for best arm identification in linearly paramete...

Bayesian Best-Arm Identification for Selecting Influenza Mitigation Strategies

Pandemic influenza has the epidemic potential to kill millions of people...

Refined bounds for randomized experimental design

Experimental design is an approach for selecting samples among a given s...