On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits

TL;DR

This paper develops a non-parametric theoretical framework for best-arm identification in multi-armed bandits with fixed budgets, introducing new bounds based on information theory that generalize previous results.

Contribution

It introduces a non-parametric theory with upper and lower bounds on misidentification probabilities using Kullback-Leibler divergences, extending existing parametric bounds.

Findings

Provides upper bounds on misidentification probability using KL divergence.

Establishes lower bounds that match the upper bounds under certain conditions.

Generalizes existing bounds based on distribution gaps.

Abstract

We lay the foundations of a non-parametric theory of best-arm identification in multi-armed bandits with a fixed budget T. We consider general, possibly non-parametric, models D for distributions over the arms; an overarching example is the model D = P(0,1) of all probability distributions over [0,1]. We propose upper bounds on the average log-probability of misidentifying the optimal arm based on information-theoretic quantities that correspond to infima over Kullback-Leibler divergences between some distributions in D and a given distribution. This is made possible by a refined analysis of the successive-rejects strategy of Audibert, Bubeck, and Munos (2010). We finally provide lower bounds on the same average log-probability, also in terms of the same new information-theoretic quantities; these lower bounds are larger when the (natural) assumptions on the considered strategies are stronger. All these new upper and lower bounds generalize existing bounds based, e.g., on gaps between distributions.