Hyper-parameter handling for Gaussian processes in efficient global optimization

Research output: Chapter in Book/Report/Conference proceedingsConference contributionpeer-review

Abstract

In simulation-based optimization, a common issue with many meta-heuristic algorithms is the limited computational budget. Performing a simulation is usually considerably more time-consuming than evaluating a closed mathematical function. Surrogate-assisted algorithms alleviate this problem by using representative models of the simulation which can be evaluated much faster. One of the most promising surrogate-assisted optimization approaches is Efficient Global Optimization, which uses Gaussian processes as surrogate-models. In this paper, the importance of carefully chosen hyper-parameters for Gaussian process kernels and a way of self-configuration is shown. Based on properties of the training set, e.g. distances between observed points, observed target values, etc., the hyper-parameters of the used kernels are initialized and bounded accordingly. With these initial values and bounds in mind, hyper-parameters are then optimized, which results in improved Gaussian process models that can be used for regression. The goal is to provide an automated way of hyper-parameter initialization, which can be used when building Kriging models in surrogate-assisted algorithms, e.g. Efficient Global Optimization (EGO). Obtained results show that applying the proposed hyper-parameter initialization and bounding can increase the performance of EGO in terms of either convergence speed or achieved objective function value.

Original languageEnglish
Title of host publication19th International Conference on Modeling and Applied Simulation, MAS 2020
EditorsAgostino G. Bruzzone, Fabio De Felice, Marina Massei, Adriano Solis
PublisherDIME UNIVERSITY OF GENOA
Pages60-67
Number of pages8
ISBN (Electronic)9788885741492
DOIs
Publication statusPublished - 2020
Event19th International Conference on Modeling and Applied Simulation, MAS 2020 - Virtual, Online
Duration: 16 Sep 202018 Sep 2020

Publication series

Name19th International Conference on Modeling and Applied Simulation, MAS 2020

Conference

Conference19th International Conference on Modeling and Applied Simulation, MAS 2020
CityVirtual, Online
Period16.09.202018.09.2020

Keywords

  • Efficient Global Optimization
  • Gaussian Process
  • Hyper-Parameter
  • Self-Configuration

Fingerprint

Dive into the research topics of 'Hyper-parameter handling for Gaussian processes in efficient global optimization'. Together they form a unique fingerprint.

Cite this