Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/70658
Título: | Complexity of gradient descent for multiobjective optimization |
Autor(es): | Fliege, J. Vaz, A. Ismael F. Vicente, Luís Nunes |
Palavras-chave: | Multiobjective optimization Gradient descent Steepest descent Global rates Worst-case complexity |
Data: | 2019 |
Editora: | Taylor and Francis |
Revista: | Optimization Methods & Software |
Resumo(s): | 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 worstcase complexity bounds. In the convex cases, the rates are given for implicit scalarizations of the problem vector function. |
Tipo: | Artigo |
Descrição: | Published online: 29 Aug 2018 |
URI: | https://hdl.handle.net/1822/70658 |
DOI: | 10.1080/10556788.2018.1510928 |
ISSN: | 1055-6788 |
e-ISSN: | 1029-4937 |
Arbitragem científica: | yes |
Acesso: | Acesso restrito UMinho |
Aparece nas coleções: | CAlg - Artigos em revistas internacionais / Papers in international journals |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
FliegeVazVicente.pdf Acesso restrito! | Paper | 1,05 MB | Adobe PDF | Ver/Abrir |