Optimization Online


A FISTA-type accelerated gradient algorithm for solving smooth nonconvex composite optimization problems

Jiaming Liang (jiaming.liang***at***gatech.edu)
Renato Monteiro (renato.monteiro***at***isye.gatech.edu)
Chee-Khian Sim (chee-khian.sim***at***port.ac.uk)

Abstract: In this paper, we describe and establish iteration-complexity of two accelerated composite gradient (ACG) variants to solve a smooth nonconvex composite optimization problem whose objective function is the sum of a nonconvex differentiable function f with a Lipschitz continuous gradient and a simple nonsmooth closed convex function h. When f is convex, the first ACG variant reduces to the well-known FISTA for a specific choice of the input, and hence the first one can be viewed as a natural extension of the latter one to the nonconvex setting. The first variant requires as input a pair (M,m), M being a Lipschitz constant of ∇f and m being a lower curvature of f such that m ≤ M (possibly m < M), which is usually hard to obtain or poorly estimated. The second variant on the other hand can start from an arbitrary input pair (M, m) of positive scalars and its complexity is shown to be not worse, and better in some cases, than that of the first variant for a large range of the input pairs. Finally, numerical results are provided to illustrate the efficiency of the two ACG variants.

Keywords: Nonconvex Optimization, Iteration-Complexity, First-Order Accelerated Method, Proximal Point Method

Category 1: Nonlinear Optimization

Category 2: Convex and Nonsmooth Optimization


Download: [PDF]

Entry Submitted: 05/16/2019
Entry Accepted: 05/16/2019
Entry Last Modified: 11/04/2019

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