Saved in:
Bibliographic Details
Main Authors: Ishibashi, Hideaki, Matsui, Kota, Kutsukake, Kentaro, Hino, Hideitsu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.20272
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909553958846464
author Ishibashi, Hideaki
Matsui, Kota
Kutsukake, Kentaro
Hino, Hideitsu
author_facet Ishibashi, Hideaki
Matsui, Kota
Kutsukake, Kentaro
Hino, Hideitsu
contents The level set estimation problem seeks to identify regions within a set of candidate points where an unknown and costly to evaluate function's value exceeds a specified threshold, providing an efficient alternative to exhaustive evaluations of function values. Traditional methods often use sequential optimization strategies to find $ε$-accurate solutions, which permit a margin around the threshold contour but frequently lack effective stopping criteria, leading to excessive exploration and inefficiencies. This paper introduces an acquisition strategy for level set estimation that incorporates a stopping criterion, ensuring the algorithm halts when further exploration is unlikely to yield improvements, thereby reducing unnecessary function evaluations. We theoretically prove that our method satisfies $ε$-accuracy with a confidence level of $1 - δ$, addressing a key gap in existing approaches. Furthermore, we show that this also leads to guarantees on the lower bounds of performance metrics such as F-score. Numerical experiments demonstrate that the proposed acquisition function achieves comparable precision to existing methods while confirming that the stopping criterion effectively terminates the algorithm once adequate exploration is completed.
format Preprint
id arxiv_https___arxiv_org_abs_2503_20272
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An $(ε,δ)$-accurate level set estimation with a stopping criterion
Ishibashi, Hideaki
Matsui, Kota
Kutsukake, Kentaro
Hino, Hideitsu
Machine Learning
The level set estimation problem seeks to identify regions within a set of candidate points where an unknown and costly to evaluate function's value exceeds a specified threshold, providing an efficient alternative to exhaustive evaluations of function values. Traditional methods often use sequential optimization strategies to find $ε$-accurate solutions, which permit a margin around the threshold contour but frequently lack effective stopping criteria, leading to excessive exploration and inefficiencies. This paper introduces an acquisition strategy for level set estimation that incorporates a stopping criterion, ensuring the algorithm halts when further exploration is unlikely to yield improvements, thereby reducing unnecessary function evaluations. We theoretically prove that our method satisfies $ε$-accuracy with a confidence level of $1 - δ$, addressing a key gap in existing approaches. Furthermore, we show that this also leads to guarantees on the lower bounds of performance metrics such as F-score. Numerical experiments demonstrate that the proposed acquisition function achieves comparable precision to existing methods while confirming that the stopping criterion effectively terminates the algorithm once adequate exploration is completed.
title An $(ε,δ)$-accurate level set estimation with a stopping criterion
topic Machine Learning
url https://arxiv.org/abs/2503.20272