Optimality Conditions and Algorithms for Top-K Arm Identification

05/24/2022
by   Zihao Wang, et al.
0

We consider the top-k arm identification problem for multi-armed bandits with rewards belonging to a one-parameter canonical exponential family. The objective is to select the set of k arms with the highest mean rewards by sequential allocation of sampling efforts. We propose a unified optimal allocation problem that identifies the complexity measures of this problem under the fixed-confidence, fixed-budget settings, and the posterior convergence rate from the Bayesian perspective. We provide the first characterization of its optimality. We provide the first provably optimal algorithm in the fixed-confidence setting for k>1. We also propose an efficient heuristic algorithm for the top-k arm identification problem. Extensive numerical experiments demonstrate superior performance compare to existing methods in all three settings.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/10/2023

Best Arm Identification in Stochastic Bandits: Beyond β-optimality

This paper focuses on best arm identification (BAI) in stochastic multi-...
research
06/12/2021

Guaranteed Fixed-Confidence Best Arm Identification in Multi-Armed Bandit

We consider the problem of finding, through adaptive sampling, which of ...
research
07/22/2022

SPRT-based Efficient Best Arm Identification in Stochastic Bandits

This paper investigates the best arm identification (BAI) problem in sto...
research
11/05/2019

Towards Optimal and Efficient Best Arm Identification in Linear Bandits

We give a new algorithm for best arm identification in linearly paramete...
research
07/09/2017

Nonlinear Sequential Accepts and Rejects for Identification of Top Arms in Stochastic Bandits

We address the M-best-arm identification problem in multi-armed bandits....
research
10/24/2019

Fixed-Confidence Guarantees for Bayesian Best-Arm Identification

We investigate and provide new insights on the sampling rule called Top-...
research
12/14/2020

Best Arm Identification in Graphical Bilinear Bandits

We introduce a new graphical bilinear bandit problem where a learner (or...

Please sign up or login with your details

Forgot password? Click here to reset