Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Tian, Yunsheng, Zuniga, Ane, Zhang, Xinwei, Dürholt, Johannes P., Das, Payel, Chen, Jie, Matusik, Wojciech, Luković, Mina Konaković
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914803643056128
author Tian, Yunsheng
Zuniga, Ane
Zhang, Xinwei
Dürholt, Johannes P.
Das, Payel
Chen, Jie
Matusik, Wojciech
Luković, Mina Konaković
author_facet Tian, Yunsheng
Zuniga, Ane
Zhang, Xinwei
Dürholt, Johannes P.
Das, Payel
Chen, Jie
Matusik, Wojciech
Luković, Mina Konaković
contents Bayesian optimization has been successfully applied to optimize black-box functions where the number of evaluations is severely limited. However, in many real-world applications, it is hard or impossible to know in advance which designs are feasible due to some physical or system limitations. These issues lead to an even more challenging problem of optimizing an unknown function with unknown constraints. In this paper, we observe that in such scenarios optimal solution typically lies on the boundary between feasible and infeasible regions of the design space, making it considerably more difficult than that with interior optima. Inspired by this observation, we propose BE-CBO, a new Bayesian optimization method that efficiently explores the boundary between feasible and infeasible designs. To identify the boundary, we learn the constraints with an ensemble of neural networks that outperform the standard Gaussian Processes for capturing complex boundaries. Our method demonstrates superior performance against state-of-the-art methods through comprehensive experiments on synthetic and real-world benchmarks. Code available at: https://github.com/yunshengtian/BE-CBO
format Preprint
id arxiv_https___arxiv_org_abs_2402_07692
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints
Tian, Yunsheng
Zuniga, Ane
Zhang, Xinwei
Dürholt, Johannes P.
Das, Payel
Chen, Jie
Matusik, Wojciech
Luković, Mina Konaković
Machine Learning
Bayesian optimization has been successfully applied to optimize black-box functions where the number of evaluations is severely limited. However, in many real-world applications, it is hard or impossible to know in advance which designs are feasible due to some physical or system limitations. These issues lead to an even more challenging problem of optimizing an unknown function with unknown constraints. In this paper, we observe that in such scenarios optimal solution typically lies on the boundary between feasible and infeasible regions of the design space, making it considerably more difficult than that with interior optima. Inspired by this observation, we propose BE-CBO, a new Bayesian optimization method that efficiently explores the boundary between feasible and infeasible designs. To identify the boundary, we learn the constraints with an ensemble of neural networks that outperform the standard Gaussian Processes for capturing complex boundaries. Our method demonstrates superior performance against state-of-the-art methods through comprehensive experiments on synthetic and real-world benchmarks. Code available at: https://github.com/yunshengtian/BE-CBO
title Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints
topic Machine Learning
url https://arxiv.org/abs/2402.07692