Saved in:
Bibliographic Details
Main Author: Ushiyama, Kansei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.09295
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914045551968256
author Ushiyama, Kansei
author_facet Ushiyama, Kansei
contents In this paper, we propose a novel accelerated forward-backward splitting algorithm for minimizing convex composite functions, written as the sum of a smooth function and a (possibly) nonsmooth function. When the objective function is strongly convex, the method attains, to the best of our knowledge, the fastest known convergence rate, yielding a simultaneous linear and sublinear nonasymptotic bound. Our convergence analysis remains valid even when one of the two terms is only weakly convex (while the sum remains convex). The algorithm is derived by discretizing a continuous-time model of the Information-Theoretic Exact Method (ITEM), which is the optimal method for unconstrained strongly convex minimization.
format Preprint
id arxiv_https___arxiv_org_abs_2509_09295
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A $\sqrt{2}$-accelerated FISTA for composite strongly convex problems
Ushiyama, Kansei
Optimization and Control
In this paper, we propose a novel accelerated forward-backward splitting algorithm for minimizing convex composite functions, written as the sum of a smooth function and a (possibly) nonsmooth function. When the objective function is strongly convex, the method attains, to the best of our knowledge, the fastest known convergence rate, yielding a simultaneous linear and sublinear nonasymptotic bound. Our convergence analysis remains valid even when one of the two terms is only weakly convex (while the sum remains convex). The algorithm is derived by discretizing a continuous-time model of the Information-Theoretic Exact Method (ITEM), which is the optimal method for unconstrained strongly convex minimization.
title A $\sqrt{2}$-accelerated FISTA for composite strongly convex problems
topic Optimization and Control
url https://arxiv.org/abs/2509.09295