No Cover Image

Conference Paper/Proceeding/Abstract 562 views

On the Impact of Covariance Functions in Multi-Objective Bayesian Optimization for Engineering Design

Pramudita S. Palar, Lavi R. Zuhal, Tinkle Chugh, Alma Rahat Orcid Logo

AIAA Scitech 2020 Forum

Swansea University Author: Alma Rahat Orcid Logo

Full text not available from this repository: check for access using links below.

DOI (Published version): 10.2514/6.2020-1867

Abstract

Multi-objective Bayesian optimization (BO) is a highly useful class of methods that can effectively solve computationally expensive engineering design optimization problems with multiple objectives. However, the impact of covariance function, which is an important part of multi-objective BO, is rare...

Full description

Published in: AIAA Scitech 2020 Forum
ISBN: 9781624105951
Published: Reston, Virginia American Institute of Aeronautics and Astronautics 2020
URI: https://cronfa.swan.ac.uk/Record/cronfa54034
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2020-05-01T19:38:32Z
last_indexed 2020-10-10T03:08:18Z
id cronfa54034
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2020-10-09T19:29:23.4562274</datestamp><bib-version>v2</bib-version><id>54034</id><entry>2020-04-24</entry><title>On the Impact of Covariance Functions in Multi-Objective Bayesian Optimization for Engineering Design</title><swanseaauthors><author><sid>6206f027aca1e3a5ff6b8cd224248bc2</sid><ORCID>0000-0002-5023-1371</ORCID><firstname>Alma</firstname><surname>Rahat</surname><name>Alma Rahat</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2020-04-24</date><deptcode>SCS</deptcode><abstract>Multi-objective Bayesian optimization (BO) is a highly useful class of methods that can effectively solve computationally expensive engineering design optimization problems with multiple objectives. However, the impact of covariance function, which is an important part of multi-objective BO, is rarely studied in the context of engineering optimization. We aim to shed light on this issue by performing numerical experiments on engineering design optimization problems, primarily low-fidelity problems so that we are able to statistically evaluate the performance of BO methods with various covariance functions. In this paper, we performed the study using a set of subsonic airfoil optimization cases as benchmark problems. Expected hypervolume improvement was used as the acquisition function to enrich the experimental design. Results show that the choice of the covariance function give a notable impact on the performance of multi-objective BO. In this regard, Kriging models with Matern-3/2 is the most robust method in terms of the diversity and convergence to the Pareto front that can handle problems with various complexities.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>AIAA Scitech 2020 Forum</journal><publisher>American Institute of Aeronautics and Astronautics</publisher><placeOfPublication>Reston, Virginia</placeOfPublication><isbnElectronic>9781624105951</isbnElectronic><keywords/><publishedDay>6</publishedDay><publishedMonth>1</publishedMonth><publishedYear>2020</publishedYear><publishedDate>2020-01-06</publishedDate><doi>10.2514/6.2020-1867</doi><url/><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2020-10-09T19:29:23.4562274</lastEdited><Created>2020-04-24T09:56:18.4370048</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Pramudita S.</firstname><surname>Palar</surname><order>1</order></author><author><firstname>Lavi R.</firstname><surname>Zuhal</surname><order>2</order></author><author><firstname>Tinkle</firstname><surname>Chugh</surname><order>3</order></author><author><firstname>Alma</firstname><surname>Rahat</surname><orcid>0000-0002-5023-1371</orcid><order>4</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2020-10-09T19:29:23.4562274 v2 54034 2020-04-24 On the Impact of Covariance Functions in Multi-Objective Bayesian Optimization for Engineering Design 6206f027aca1e3a5ff6b8cd224248bc2 0000-0002-5023-1371 Alma Rahat Alma Rahat true false 2020-04-24 SCS Multi-objective Bayesian optimization (BO) is a highly useful class of methods that can effectively solve computationally expensive engineering design optimization problems with multiple objectives. However, the impact of covariance function, which is an important part of multi-objective BO, is rarely studied in the context of engineering optimization. We aim to shed light on this issue by performing numerical experiments on engineering design optimization problems, primarily low-fidelity problems so that we are able to statistically evaluate the performance of BO methods with various covariance functions. In this paper, we performed the study using a set of subsonic airfoil optimization cases as benchmark problems. Expected hypervolume improvement was used as the acquisition function to enrich the experimental design. Results show that the choice of the covariance function give a notable impact on the performance of multi-objective BO. In this regard, Kriging models with Matern-3/2 is the most robust method in terms of the diversity and convergence to the Pareto front that can handle problems with various complexities. Conference Paper/Proceeding/Abstract AIAA Scitech 2020 Forum American Institute of Aeronautics and Astronautics Reston, Virginia 9781624105951 6 1 2020 2020-01-06 10.2514/6.2020-1867 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University 2020-10-09T19:29:23.4562274 2020-04-24T09:56:18.4370048 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Pramudita S. Palar 1 Lavi R. Zuhal 2 Tinkle Chugh 3 Alma Rahat 0000-0002-5023-1371 4
title On the Impact of Covariance Functions in Multi-Objective Bayesian Optimization for Engineering Design
spellingShingle On the Impact of Covariance Functions in Multi-Objective Bayesian Optimization for Engineering Design
Alma Rahat
title_short On the Impact of Covariance Functions in Multi-Objective Bayesian Optimization for Engineering Design
title_full On the Impact of Covariance Functions in Multi-Objective Bayesian Optimization for Engineering Design
title_fullStr On the Impact of Covariance Functions in Multi-Objective Bayesian Optimization for Engineering Design
title_full_unstemmed On the Impact of Covariance Functions in Multi-Objective Bayesian Optimization for Engineering Design
title_sort On the Impact of Covariance Functions in Multi-Objective Bayesian Optimization for Engineering Design
author_id_str_mv 6206f027aca1e3a5ff6b8cd224248bc2
author_id_fullname_str_mv 6206f027aca1e3a5ff6b8cd224248bc2_***_Alma Rahat
author Alma Rahat
author2 Pramudita S. Palar
Lavi R. Zuhal
Tinkle Chugh
Alma Rahat
format Conference Paper/Proceeding/Abstract
container_title AIAA Scitech 2020 Forum
publishDate 2020
institution Swansea University
isbn 9781624105951
doi_str_mv 10.2514/6.2020-1867
publisher American Institute of Aeronautics and Astronautics
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 0
active_str 0
description Multi-objective Bayesian optimization (BO) is a highly useful class of methods that can effectively solve computationally expensive engineering design optimization problems with multiple objectives. However, the impact of covariance function, which is an important part of multi-objective BO, is rarely studied in the context of engineering optimization. We aim to shed light on this issue by performing numerical experiments on engineering design optimization problems, primarily low-fidelity problems so that we are able to statistically evaluate the performance of BO methods with various covariance functions. In this paper, we performed the study using a set of subsonic airfoil optimization cases as benchmark problems. Expected hypervolume improvement was used as the acquisition function to enrich the experimental design. Results show that the choice of the covariance function give a notable impact on the performance of multi-objective BO. In this regard, Kriging models with Matern-3/2 is the most robust method in terms of the diversity and convergence to the Pareto front that can handle problems with various complexities.
published_date 2020-01-06T04:07:20Z
_version_ 1763753528379047936
score 11.013731

Similar Items