Optimal Nonergodic Sublinear Convergence Rate of Proximal Point Algorithm for Maximal Monotone Inclusion Problems

TL;DR

This paper precisely characterizes the best possible nonergodic sublinear convergence rate of the proximal point algorithm for maximal monotone inclusion problems, using performance estimation and SDP techniques.

Contribution

It establishes the exact optimal nonergodic sublinear convergence rate for the proximal point algorithm, matching upper and lower bounds through novel SDP reformulation.

Findings

Optimal nonergodic sublinear convergence rate derived

Upper and lower bounds match exactly

Provides sharp understanding of proximal point algorithm performance

Abstract

We establish the optimal nonergodic sublinear convergence rate of the proximal point algorithm for maximal monotone inclusion problems. First, the optimal bound is formulated by the performance estimation framework, resulting in an infinite dimensional nonconvex optimization problem, which is then equivalently reformulated as a finite dimensional semidefinite programming (SDP) problem. By constructing a feasible solution to the dual SDP, we obtain an upper bound on the optimal nonergodic sublinear rate. Finally, an example in two dimensional space is constructed to provide a lower bound on the optimal nonergodic sublinear rate. Since the lower bound provided by the example matches exactly the upper bound obtained by the dual SDP, we have thus established the worst case nonergodic sublinear convergence rate which is optimal in terms of both the order as well as the constants involved. Our result sharpens the understanding of the fundamental proximal point algorithm.