Optimization Online


An Average Curvature Accelerated Composite Gradient Method for Nonconvex Smooth Composite Optimization Problems

Jiaming Liang (jiaming.liang***at***gatech.edu)
Renato D.C. Monteiro (renato.monteiro***at***isye.gatech.edu)

Abstract: This paper presents an accelerated composite gradient (ACG) variant, referred to as the AC-ACG method, for solving nonconvex smooth composite minimization problems. As opposed to well-known ACG variants that are either based on a known Lipschitz gradient constant or a sequence of maximum observed curvatures, the current one is based on a sequence of average observed curvatures. More specifically, AC-ACG uses a positive multiple of the average of all observed curvatures until the previous iteration as a way to estimate the "function curvature" at the current point and then two resolvent evaluations to compute the next iterate. In contrast to other variable Lipschitz estimation variants, e.g, the ones based on the maximum curvature, AC-ACG always accepts the aforementioned iterate regardless how poor the Lipschitz estimation turns out to be. Finally, computational results are presented to illustrate the efficiency of AC-ACG on both randomly generated and real-world problem instances.

Keywords: Nonconvex Optimization, Average Curvature, Accelerated Composite Gradient Method

Category 1: Nonlinear Optimization

Category 2: Convex and Nonsmooth Optimization


Download: [PDF]

Entry Submitted: 09/09/2019
Entry Accepted: 09/09/2019
Entry Last Modified: 09/16/2020

Modify/Update this entry

  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository


Coordinator's Board
Classification Scheme
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society