Journal
OPTIMIZATION METHODS & SOFTWARE
Volume 34, Issue 5, Pages 949-959Publisher
TAYLOR & FRANCIS LTD
DOI: 10.1080/10556788.2018.1510928
Keywords
Multiobjective optimization; gradient descent; steepest descent; global rates; worst-case complexity
Categories
Funding
- FCT [COMPETE: POCI-010145-FEDER-007043, UID/MAT/00324/2013, UID/CEC/00319/2013, P2020 SAICTPAC/0011/2015]
- Fundação para a Ciência e a Tecnologia [UID/MAT/00324/2013] Funding Source: FCT
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available