Saved in:
Bibliographic Details
Main Authors: Stenger, David, Lindicke, Armin, von Rohr, Alexander, Trimpe, Sebastian
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.19241
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917101390790656
author Stenger, David
Lindicke, Armin
von Rohr, Alexander
Trimpe, Sebastian
author_facet Stenger, David
Lindicke, Armin
von Rohr, Alexander
Trimpe, Sebastian
contents Searching large and complex design spaces for a global optimum can be infeasible and unnecessary. A practical alternative is to iteratively refine the neighborhood of an initial design using local optimization methods such as gradient descent. We propose local entropy search (LES), a Bayesian optimization paradigm that explicitly targets the solutions reachable by the descent sequences of iterative optimizers. The algorithm propagates the posterior belief over the objective through the optimizer, resulting in a probability distribution over descent sequences. It then selects the next evaluation by maximizing mutual information with that distribution, using a combination of analytic entropy calculations and Monte-Carlo sampling of descent sequences. Empirical results on high-complexity synthetic objectives and benchmark problems show that LES achieves strong sample efficiency compared to existing local and global Bayesian optimization methods.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19241
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Local Entropy Search over Descent Sequences for Bayesian Optimization
Stenger, David
Lindicke, Armin
von Rohr, Alexander
Trimpe, Sebastian
Machine Learning
Artificial Intelligence
Searching large and complex design spaces for a global optimum can be infeasible and unnecessary. A practical alternative is to iteratively refine the neighborhood of an initial design using local optimization methods such as gradient descent. We propose local entropy search (LES), a Bayesian optimization paradigm that explicitly targets the solutions reachable by the descent sequences of iterative optimizers. The algorithm propagates the posterior belief over the objective through the optimizer, resulting in a probability distribution over descent sequences. It then selects the next evaluation by maximizing mutual information with that distribution, using a combination of analytic entropy calculations and Monte-Carlo sampling of descent sequences. Empirical results on high-complexity synthetic objectives and benchmark problems show that LES achieves strong sample efficiency compared to existing local and global Bayesian optimization methods.
title Local Entropy Search over Descent Sequences for Bayesian Optimization
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2511.19241