1. Convergence Rates for Projective Splitting
- Author
-
Jonathan Eckstein and Patrick R. Johnstone
- Subjects
FOS: Computer and information sciences ,Computer Science - Machine Learning ,Pure mathematics ,021103 operations research ,Weak convergence ,0211 other engineering and technologies ,Monotonic function ,010103 numerical & computational mathematics ,02 engineering and technology ,Strongly monotone ,01 natural sciences ,Machine Learning (cs.LG) ,Theoretical Computer Science ,Monotone polygon ,Rate of convergence ,Optimization and Control (math.OC) ,Iterated function ,Convergence (routing) ,FOS: Mathematics ,Ergodic theory ,0101 mathematics ,Mathematics - Optimization and Control ,Software ,Mathematics - Abstract
Projective splitting is a family of methods for solving inclusions involving sums of maximal monotone operators. First introduced by Eckstein and Svaiter in 2008, these methods have enjoyed significant innovation in recent years, becoming one of the most flexible operator splitting frameworks available. While weak convergence of the iterates to a solution has been established, there have been few attempts to study convergence rates of projective splitting. The purpose of this paper is to do so under various assumptions. To this end, there are three main contributions. First, in the context of convex optimization, we establish an $O(1/k)$ ergodic function convergence rate. Second, for strongly monotone inclusions, strong convergence is established as well as an ergodic $O(1/\sqrt{k})$ convergence rate for the distance of the iterates to the solution. Finally, for inclusions featuring strong monotonicity and cocoercivity, linear convergence is established., Comment: This version adds references to the extragradient method
- Published
- 2019
- Full Text
- View/download PDF