-

 

 

 




Optimization Online





 

TREGO: a Trust-Region Framework for Efficient Global Optimization

Y. Diouane (youssef.diouane***at***isae-supaero.fr)
V. Picheny (victor***at***secondmind.ai)
R. Le Riche (leriche***at***emse.fr)
A. Scotto Di Perrotolo (alexandre.scotto-di-perrotolo***at***isae-supaero.fr)

Abstract: Efficient Global Optimization (EGO) is the canonical form of Bayesian optimization that has been successfully applied to solve global optimization of expensive-to-evaluate black-box problems. However, EGO struggles to scale with dimension, and offers limited theoretical guarantees. In this work, we propose and analyze a trust-region-like EGO method (TREGO). TREGO alternates between regular EGO steps and local steps within a trust region. By following a classical scheme for the trust region (based on a sufficient decrease condition), we demonstrate that our algorithm enjoys strong global convergence properties, while departing from EGO only for a subset of optimization steps. Using extensive numerical experiments based on the well-known COCO benchmark, we first analyze the sensitivity of TREGO to its own parameters, then show that the resulting algorithm is consistently outperforming EGO and getting competitive with other state-of-the-art global optimization methods. The method is available both in the R package DiceOptim (https://cran.r-project.org/package=DiceOptim) and Python library trieste (https://secondmind-labs.github.io/trieste/).

Keywords: nonlinear optimization; Gaussian processes; Bayesian optimization; trust-region.

Category 1: Global Optimization

Citation:

Download: [PDF]

Entry Submitted: 01/17/2021
Entry Accepted: 01/18/2021
Entry Last Modified: 02/02/2021

Modify/Update this entry


  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository

 

Submit
Update
Policies
Coordinator's Board
Classification Scheme
Credits
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society