Revisiting norm optimization for multi-objective black-box problems : a finite-time analysis

The complexity of Pareto fronts imposes a great challenge on the convergence analysis of multi-objective optimization methods. While most theoretical convergence studies have addressed finite-set and/or discrete problems, others have provided probabilistic guarantees, assumed a total order on the so...

Full description

Bibliographic Details
Main Authors: Al-Dujaili, Abdullah, Suresh, Sundaram
Other Authors: School of Computer Science and Engineering
Format: Journal Article
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/143267
_version_ 1811687144680325120
author Al-Dujaili, Abdullah
Suresh, Sundaram
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Al-Dujaili, Abdullah
Suresh, Sundaram
author_sort Al-Dujaili, Abdullah
collection NTU
description The complexity of Pareto fronts imposes a great challenge on the convergence analysis of multi-objective optimization methods. While most theoretical convergence studies have addressed finite-set and/or discrete problems, others have provided probabilistic guarantees, assumed a total order on the solutions, or studied their asymptotic behaviour. In this paper, we revisit the Tchebycheff weighted method in a hierarchical bandits setting and provide a finite-time bound on the Pareto-compliant additive ϵ-indicator. To the best of our knowledge, this paper is one of few that establish a link between weighted sum methods and quality indicators in finite time.
first_indexed 2024-10-01T05:11:39Z
format Journal Article
id ntu-10356/143267
institution Nanyang Technological University
language English
last_indexed 2024-10-01T05:11:39Z
publishDate 2020
record_format dspace
spelling ntu-10356/1432672020-08-18T04:34:11Z Revisiting norm optimization for multi-objective black-box problems : a finite-time analysis Al-Dujaili, Abdullah Suresh, Sundaram School of Computer Science and Engineering Engineering::Computer science and engineering Multi-objective Optimization Black-box Optimization The complexity of Pareto fronts imposes a great challenge on the convergence analysis of multi-objective optimization methods. While most theoretical convergence studies have addressed finite-set and/or discrete problems, others have provided probabilistic guarantees, assumed a total order on the solutions, or studied their asymptotic behaviour. In this paper, we revisit the Tchebycheff weighted method in a hierarchical bandits setting and provide a finite-time bound on the Pareto-compliant additive ϵ-indicator. To the best of our knowledge, this paper is one of few that establish a link between weighted sum methods and quality indicators in finite time. Accepted version 2020-08-18T04:34:11Z 2020-08-18T04:34:11Z 2018 Journal Article Al-Dujaili, A., & Suresh, S. (2019). Revisiting norm optimization for multi-objective black-box problems : a finite-time analysis. Journal of Global Optimization, 73(3), 659-673. doi:10.1007/s10898-018-0709-z 0925-5001 https://hdl.handle.net/10356/143267 10.1007/s10898-018-0709-z 2-s2.0-85054316678 3 73 659 673 en Journal of Global Optimization © 2018 Springer. This is a post-peer-review, pre-copyedit version of an article published in Journal of Global Optimization. The final authenticated version is available online at: http://dx.doi.org/10.1007/s10898-018-0709-z. application/pdf
spellingShingle Engineering::Computer science and engineering
Multi-objective Optimization
Black-box Optimization
Al-Dujaili, Abdullah
Suresh, Sundaram
Revisiting norm optimization for multi-objective black-box problems : a finite-time analysis
title Revisiting norm optimization for multi-objective black-box problems : a finite-time analysis
title_full Revisiting norm optimization for multi-objective black-box problems : a finite-time analysis
title_fullStr Revisiting norm optimization for multi-objective black-box problems : a finite-time analysis
title_full_unstemmed Revisiting norm optimization for multi-objective black-box problems : a finite-time analysis
title_short Revisiting norm optimization for multi-objective black-box problems : a finite-time analysis
title_sort revisiting norm optimization for multi objective black box problems a finite time analysis
topic Engineering::Computer science and engineering
Multi-objective Optimization
Black-box Optimization
url https://hdl.handle.net/10356/143267
work_keys_str_mv AT aldujailiabdullah revisitingnormoptimizationformultiobjectiveblackboxproblemsafinitetimeanalysis
AT sureshsundaram revisitingnormoptimizationformultiobjectiveblackboxproblemsafinitetimeanalysis