Saved in:
Bibliographic Details
Main Authors: Jin, Tianyuan, Zhang, Qin, Zhou, Dongruo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.17370
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912208585228288
author Jin, Tianyuan
Zhang, Qin
Zhou, Dongruo
author_facet Jin, Tianyuan
Zhang, Qin
Zhou, Dongruo
contents We investigate the problem of batched best arm identification in multi-armed bandits, where we aim to identify the best arm from a set of $n$ arms while minimizing both the number of samples and batches. We introduce an algorithm that achieves near-optimal sample complexity and features an instance-sensitive batch complexity, which breaks the $\log(1/Δ_2)$ barrier. The main contribution of our algorithm is a novel sample allocation scheme that effectively balances exploration and exploitation for batch sizes. Experimental results indicate that our approach is more batch-efficient across various setups. We also extend this framework to the problem of batched best arm identification in linear bandits and achieve similar improvements.
format Preprint
id arxiv_https___arxiv_org_abs_2501_17370
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Breaking the $\log(1/Δ_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids
Jin, Tianyuan
Zhang, Qin
Zhou, Dongruo
Machine Learning
We investigate the problem of batched best arm identification in multi-armed bandits, where we aim to identify the best arm from a set of $n$ arms while minimizing both the number of samples and batches. We introduce an algorithm that achieves near-optimal sample complexity and features an instance-sensitive batch complexity, which breaks the $\log(1/Δ_2)$ barrier. The main contribution of our algorithm is a novel sample allocation scheme that effectively balances exploration and exploitation for batch sizes. Experimental results indicate that our approach is more batch-efficient across various setups. We also extend this framework to the problem of batched best arm identification in linear bandits and achieve similar improvements.
title Breaking the $\log(1/Δ_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids
topic Machine Learning
url https://arxiv.org/abs/2501.17370