This is not the latest version of this item. The latest version can be found here.
Bayesian optimization with output-weighted optimal sampling
Name
2004.10599.pdf
Description
Accepted version
Size
1.37 MB
Format
Adobe PDF
Checksum (MD5)
f0862326fd66b6eefe5b0ee8da455034
Author(s)
Blanchard, Antoine
Sapsis, Themistoklis
Date Issued
2021
Journal
Journal of Computational Physics
Publisher
Elsevier BV
Citation
Blanchard, Antoine and Sapsis, Themistoklis. 2021. "Bayesian optimization with output-weighted optimal sampling." Journal of Computational Physics, 425.
Version
Author's final manuscript
Abstract
© 2020 Elsevier Inc. In Bayesian optimization, accounting for the importance of the output relative to the input is a crucial yet challenging exercise, as it can considerably improve the final result but often involves inaccurate and cumbersome entropy estimations. We approach the problem from the perspective of importance-sampling theory, and advocate the use of the likelihood ratio to guide the search algorithm towards regions of the input space where the objective function to minimize assumes abnormally small values. The likelihood ratio acts as a sampling weight and can be computed at each iteration without severely deteriorating the overall efficiency of the algorithm. In particular, it can be approximated in a way that makes the approach tractable in high dimensions. The “likelihood-weighted” acquisition functions introduced in this work are found to outperform their unweighted counterparts in a number of applications.
Terms of Use
Creative Commons Attribution-NonCommercial-NoDerivs License
Persistent DSpace Link
DOI of Published Version
10.1016/J.JCP.2020.109901
