An inexact linearized proximal algorithm for a class of DC composite optimization problems and applications

by   Ting Tao, et al.

This paper is concerned with a class of DC composite optimization problems which, as an extension of the convex composite optimization problem and the DC program with nonsmooth components, often arises from robust factorization models of low-rank matrix recovery. For this class of nonconvex and nonsmooth problems, we propose an inexact linearized proximal algorithm (iLPA) which in each step computes an inexact minimizer of a strongly convex majorization constructed by the partial linearization of their objective functions. The generated iterate sequence is shown to be convergent under the Kurdyka-Łojasiewicz (KL) property of a potential function, and the convergence admits a local R-linear rate if the potential function has the KL property of exponent 1/2 at the limit point. For the latter assumption, we provide a verifiable condition by leveraging the composite structure, and clarify its relation with the regularity used for the convex composite optimization. Finally, the proposed iLPA is applied to a robust factorization model for matrix completions with outliers, DC programs with nonsmooth components, and ℓ_1-norm exact penalty of DC constrained programs, and numerical comparison with the existing algorithms confirms the superiority of our iLPA in computing time and quality of solutions.


page 1

page 2

page 3

page 4


KL property of exponent 1/2 of ℓ_2,0-norm and DC regularized factorizations for low-rank matrix recovery

This paper is concerned with the factorization form of the rank regulari...

Proximal algorithms for constrained composite optimization, with applications to solving low-rank SDPs

We study a family of (potentially non-convex) constrained optimization p...

A refined convergence analysis of pDCA_e with applications to simultaneous sparse recovery and outlier detection

We consider the problem of minimizing a difference-of-convex (DC) functi...

Global Convergence of Model Function Based Bregman Proximal Minimization Algorithms

Lipschitz continuity of the gradient mapping of a continuously different...

AC/DC: In-Database Learning Thunderstruck

We report on the design and implementation of the AC/DC gradient descent...

Calculus of the exponent of Kurdyka-Łojasiewicz inequality and its applications to linear convergence of first-order methods

In this paper, we study the Kurdyka-Łojasiewicz (KL) exponent, an import...

Constrained and Composite Optimization via Adaptive Sampling Methods

The motivation for this paper stems from the desire to develop an adapti...

Please sign up or login with your details

Forgot password? Click here to reset