Surrogate modeling for Bayesian optimization beyond a single Gaussian process

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Qin, Polyzos, Konstantinos D., Li, Bingcong, Giannakis, Georgios B.
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917536861257728
author Lu, Qin
Polyzos, Konstantinos D.
Li, Bingcong
Giannakis, Georgios B.
author_facet Lu, Qin
Polyzos, Konstantinos D.
Li, Bingcong
Giannakis, Georgios B.
contents Bayesian optimization (BO) has well-documented merits for optimizing black-box functions with an expensive evaluation cost. Such functions emerge in applications as diverse as hyperparameter tuning, drug discovery, and robotics. BO hinges on a Bayesian surrogate model to sequentially select query points so as to balance exploration with exploitation of the search space. Most existing works rely on a single Gaussian process (GP) based surrogate model, where the kernel function form is typically preselected using domain knowledge. To bypass such a design process, this paper leverages an ensemble (E) of GPs to adaptively select the surrogate model fit on-the-fly, yielding a GP mixture posterior with enhanced expressiveness for the sought function. Acquisition of the next evaluation input using this EGP-based function posterior is then enabled by Thompson sampling (TS) that requires no additional design parameters. To endow function sampling with scalability, random feature-based kernel approximation is leveraged per GP model. The novel EGP-TS readily accommodates parallel operation. To further establish convergence of the proposed EGP-TS to the global optimum, analysis is conducted based on the notion of Bayesian regret for both sequential and parallel settings. Tests on synthetic functions and real-world applications showcase the merits of the proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2205_14090
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Surrogate modeling for Bayesian optimization beyond a single Gaussian process
Lu, Qin
Polyzos, Konstantinos D.
Li, Bingcong
Giannakis, Georgios B.
Machine Learning
Bayesian optimization (BO) has well-documented merits for optimizing black-box functions with an expensive evaluation cost. Such functions emerge in applications as diverse as hyperparameter tuning, drug discovery, and robotics. BO hinges on a Bayesian surrogate model to sequentially select query points so as to balance exploration with exploitation of the search space. Most existing works rely on a single Gaussian process (GP) based surrogate model, where the kernel function form is typically preselected using domain knowledge. To bypass such a design process, this paper leverages an ensemble (E) of GPs to adaptively select the surrogate model fit on-the-fly, yielding a GP mixture posterior with enhanced expressiveness for the sought function. Acquisition of the next evaluation input using this EGP-based function posterior is then enabled by Thompson sampling (TS) that requires no additional design parameters. To endow function sampling with scalability, random feature-based kernel approximation is leveraged per GP model. The novel EGP-TS readily accommodates parallel operation. To further establish convergence of the proposed EGP-TS to the global optimum, analysis is conducted based on the notion of Bayesian regret for both sequential and parallel settings. Tests on synthetic functions and real-world applications showcase the merits of the proposed method.
title Surrogate modeling for Bayesian optimization beyond a single Gaussian process
topic Machine Learning
url https://arxiv.org/abs/2205.14090