Fast Reflected Forward-Backward algorithm: achieving fast convergence rates for convex optimization with linear cone constraints

TL;DR

The paper introduces a Fast Reflected Forward-Backward algorithm with Nesterov momentum that achieves accelerated convergence rates for convex optimization problems with linear cone constraints, outperforming existing methods.

Contribution

It extends reflected forward-backward methods by incorporating momentum and correction terms, providing the fastest known convergence rates for this class of problems.

Findings

Achieves $o(1/k)$ convergence rate for last-iterate in convex optimization.

Demonstrates improved convergence in minimax problems with smooth coupling.

Provides a fully splitting primal-dual algorithm with competitive theoretical guarantees.

Abstract

In this paper, we derive a Fast Reflected Forward-Backward (Fast RFB) algorithm to solve the problem of finding a zero of the sum of a maximally monotone operator and a monotone and Lipschitz continuous operator in a real Hilbert space. Our approach extends the class of reflected forward-backward methods by introducing a Nesterov momentum term and a correction term, resulting in enhanced convergence performance. The iterative sequence of the proposed algorithm is proven to converge weakly, and the Fast RFB algorithm demonstrates impressive convergence rates, achieving $o\left( \frac{1}{k} \right)$ as $k \to +\infty$ for both the discrete velocity and the tangent residual at the \emph{last-iterate}. When applied to minimax problems with a smooth coupling term and nonsmooth convex regularizers, the resulting algorithm demonstrates significantly improved convergence properties compared to the current state of the art in the literature. For convex optimization problems with linear cone constraints, our approach yields a fully splitting primal-dual algorithm that ensures not only the convergence of iterates to a primal-dual solution, but also a \emph{last-iterate} convergence rate of $o\left( \frac{1}{k} \right)$ as $k \to +\infty$ for the objective function value, feasibility measure, and complementarity condition. This represents the most competitive theoretical result currently known for algorithms addressing this class of optimization problems. Numerical experiments are performed to illustrate the convergence behavior of Fast RFB.