Complexity of gradient descent for multiobjective optimization (Preprint)

  <Reference List>
Type: Preprint
National /International: International
Title: Complexity of gradient descent for multiobjective optimization
Publication Date: 2018-04-16
Authors: - Jorg Fliege
- A. Ismael F. Vaz
- Luís Nunes Vicente
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 analyze 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.

Institution: DMUC 18-12
Online version: http://www.mat.uc.pt...prints/eng_2018.html
Download: Not available
 
© Centre for Mathematics, University of Coimbra, funded by
Science and Technology Foundation
Powered by: rdOnWeb v1.4 | technical support