Hybrid Method for Constrained Bayesian Optimization-Reference-Cited by-同舟云学术

Hybrid Method for Constrained Bayesian Optimization

Published:2023-01-03 Issue: Volume: Page:
ISSN:
Container-title:
language:
Short-container-title:

Author:

Chowdhury Raju¹,Upadhye Neelesh S¹

Affiliation:

1. Indian Institute of Technology Madras

Abstract

AbstractIn this article, we propose a hybrid Bayesian Optimization framework using an indicator function to solve constrained optimization problems efficiently. In our hybrid method, the revised acquisition function is used to effectively guide the search that explores both the feasible and infeasible regions.We demonstrate the proposed method on five test problems, including two black-box problems, to evaluate the performance of our hybrid method and compare the results to hybrid methods based on Augmented Lagrangian and Log-barrier.

Publisher

Research Square Platform LLC

Reference31 articles.

1. Ariafar, Setareh and Coll-Font, Jaume and Brooks, Dana H and Dy, Jennifer G (2019) {``ADMMBO: Bayesian optimization with unknown constraints using ADMM."}. J. Mach. Learn. Res. 20(123): 1-26

2. Boyd, Stephen and Parikh, Neal and Chu, Eric and Peleato, Borja and Eckstein, Jonathan and others (2011) {``Distributed optimization and statistical learning via the alternating direction method of multipliers"}. Foundations and Trends{\textregistered} in Machine learning 3(1): 1--122 Now Publishers, Inc.

3. Brochu, Eric and Cora, Vlad M. and de Freitas, Nando. {``A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning"}. https://arxiv.org/abs/1012.2599. 2010, arXiv, 10.48550/ARXIV.1012.2599

4. Conn, Andrew R and Scheinberg, Katya and Vicente, Luis N (2009) Introduction to derivative-free optimization. SIAM, Philadelphia, PA

5. Cox, D.D. and John, S. (1992) {``A statistical method for global optimization"}. 10.1109/ICSMC.1992.271617, 1241-1246 vol.2, , , [Proceedings] 1992 IEEE International Conference on Systems, Man, and Cybernetics