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 SizeFormat
wcc-moo-1.pdf251.38 kBAdobe PDFView/Open
Show full item record

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.