Linear convergence of inexact descent method and inexact proximal gradient algorithms for lower-order regularization problems

TL;DR

This paper proves linear convergence of inexact descent and proximal gradient algorithms for solving the non-convex _p regularization problem, including extensions to infinite-dimensional spaces, under certain optimality conditions.

Contribution

It establishes the linear convergence of inexact algorithms for _p regularization problems using second-order optimality and growth conditions, extending results to infinite-dimensional spaces.

Findings

Linear convergence to a local minimal value.

Linear convergence to a local minimum.

Extension of convergence results to infinite-dimensional Hilbert spaces.

Abstract

The $\ell_p$ regularization problem with $0< p< 1$ has been widely studied for finding sparse solutions of linear inverse problems and gained successful applications in various mathematics and applied science fields. The proximal gradient algorithm is one of the most popular algorithms for solving the $\ell_p$ regularisation problem. In the present paper, we investigate the linear convergence issue of one inexact descent method and two inexact proximal gradient algorithms (PGA). For this purpose, an optimality condition theorem is explored to provide the equivalences among a local minimum, second-order optimality condition and second-order growth property of the $\ell_p$ regularization problem. By virtue of the second-order optimality condition and second-order growth property, we establish the linear convergence properties of the inexact descent method and inexact PGAs under some simple assumptions. Both linear convergence to a local minimal value and linear convergence to a local minimum are provided. Finally, the linear convergence results of the inexact numerical methods are extended to the infinite-dimensional Hilbert spaces.