English

Average Curvature FISTA for Nonconvex Smooth Composite Optimization Problems

Optimization and Control 2023-02-07 v4

Abstract

A previous authors' paper introduces an accelerated composite gradient (ACG) variant, namely AC-ACG, for solving nonconvex smooth composite optimization (N-SCO) problems. In contrast to other ACG variants, AC-ACG estimates the local upper curvature of the N-SCO problem by using the average of the observed upper-Lipschitz curvatures obtained during the previous iterations, and uses this estimation and two composite resolvent evaluations to compute the next iterate. This paper presents an alternative FISTA-type ACG variant, namely AC-FISTA, which has the following additional features: i) it performs an average of one composite resolvent evaluation per iteration; and ii) it estimates the local upper curvature by using the average of the previously observed upper (instead of upper-Lipschitz) curvatures. These two properties acting together yield a practical AC-FISTA variant which substantially outperforms earlier ACG variants, including the AC-ACG variants discussed in the aforementioned authors' paper.

Keywords

Cite

@article{arxiv.2105.06436,
  title  = {Average Curvature FISTA for Nonconvex Smooth Composite Optimization Problems},
  author = {Jiaming Liang and Renato D. C. Monteiro},
  journal= {arXiv preprint arXiv:2105.06436},
  year   = {2023}
}

Comments

24 pages

R2 v1 2026-06-24T02:05:19.423Z