Saved in:
Bibliographic Details
Main Authors: Hwang, Seohwa, Park, Junyong
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.18186
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918347659018240
author Hwang, Seohwa
Park, Junyong
author_facet Hwang, Seohwa
Park, Junyong
contents We introduce Box Thirding (B3), a flexible and efficient algorithm for Best Arm Identification (BAI) under fixed-budget constraints. It is designed for both anytime BAI and scenarios with large N, where the number of arms is too large for exhaustive evaluation within a limited budget T. The algorithm employs an iterative ternary comparison: in each iteration, three arms are compared--the best-performing arm is explored further, the median is deferred for future comparisons, and the weakest is discarded. Even without prior knowledge of T, B3 achieves an epsilon-best arm misidentification probability comparable to Successive Halving (SH), which requires T as a predefined parameter, applied to a randomly selected subset of c0 arms that fit within the budget. Empirical results show that B3 outperforms existing methods under limited-budget constraints in terms of simple regret, as demonstrated on the New Yorker Cartoon Caption Contest dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2602_18186
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Box Thirding: Anytime Best Arm Identification under Insufficient Sampling
Hwang, Seohwa
Park, Junyong
Machine Learning
62L05
We introduce Box Thirding (B3), a flexible and efficient algorithm for Best Arm Identification (BAI) under fixed-budget constraints. It is designed for both anytime BAI and scenarios with large N, where the number of arms is too large for exhaustive evaluation within a limited budget T. The algorithm employs an iterative ternary comparison: in each iteration, three arms are compared--the best-performing arm is explored further, the median is deferred for future comparisons, and the weakest is discarded. Even without prior knowledge of T, B3 achieves an epsilon-best arm misidentification probability comparable to Successive Halving (SH), which requires T as a predefined parameter, applied to a randomly selected subset of c0 arms that fit within the budget. Empirical results show that B3 outperforms existing methods under limited-budget constraints in terms of simple regret, as demonstrated on the New Yorker Cartoon Caption Contest dataset.
title Box Thirding: Anytime Best Arm Identification under Insufficient Sampling
topic Machine Learning
62L05
url https://arxiv.org/abs/2602.18186