Please use this identifier to cite or link to this item:
https://hdl.handle.net/10316/89443
Title: | Complexity of gradient descent for multiobjective optimization | Authors: | Fliege, Jörg Vaz, António Ismael Freitas Vicente, Luís Nunes |
Keywords: | Multiobjective optimization; gradient descent; steepest descent; global rates; worst-case complexity | Issue Date: | 2019 | Publisher: | Taylor & Francis | Project: | CMUC-UID/MAT/00324/2013 | metadata.degois.publication.title: | Optimization Methods and Software | metadata.degois.publication.volume: | 34 | metadata.degois.publication.issue: | 5 | Abstract: | A number of first-order methods have been proposed for smooth multiobjective optimization for which some form of convergence to first-order criticality has been proved. Such convergence is global in the sense of being independent of the starting point. In this paper, we analyse the rate of convergence of gradient descent for smooth unconstrained multiobjective optimization, and we do it for non-convex, convex, and strongly convex vector functions. These global rates are shown to be the same as for gradient descent in single-objective optimization and correspond to appropriate worst-case complexity bounds. In the convex cases, the rates are given for implicit scalarizations of the problem vector function. | URI: | https://hdl.handle.net/10316/89443 | DOI: | 10.1080/10556788.2018.1510928 | Rights: | embargoedAccess |
Appears in Collections: | I&D CMUC - Artigos em Revistas Internacionais |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
wcc-moo-1.pdf | 251.38 kB | Adobe PDF | View/Open |
SCOPUSTM
Citations
54
checked on May 27, 2024
WEB OF SCIENCETM
Citations
10
57
checked on Nov 2, 2024
Page view(s)
197
checked on Oct 30, 2024
Download(s)
454
checked on Oct 30, 2024
Google ScholarTM
Check
Altmetric
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.