Abstract:Bayesian Optimization (BO) is a principled framework for optimizing expensive black-box functions, with Expected Improvement (EI) among its most widely used acquisition functions. Despite its empirical success, EI is agnostic to first-order optimality conditions, relying solely on objective-value improvement. As a result, it can exhibit vanishing acquisition signals where the improvement criterion is uninformative, limiting its effectiveness in guiding search. We propose Expected Improvement via Gradient Norms (EI-GN), a novel acquisition function that extends the improvement principle to incorporate first-order stationarity, promoting sampling in regions that are both high-performing and close to stationary points. We derive a tractable closed-form expression for EI-GN and show that it remains consistent with the improvement-based acquisition framework. By embedding progress toward stationarity into the acquisition criterion, EI-GN provides a richer and more informative notion of improvement. Empirical results on standard BO benchmarks demonstrate consistent gains over baseline methods, and we further illustrate its applicability to control policy learning.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2601.21357 [cs.LG] |
| (or arXiv:2601.21357v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2601.21357 arXiv-issued DOI via DataCite |
From: Joshua Hang Sai Ip [view email]
[v1]
Thu, 29 Jan 2026 07:37:13 UTC (937 KB)
[v2]
Thu, 14 May 2026 19:44:18 UTC (646 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。