A Unified Framework for Solving a General Class of Nonconvexly Regularized Convex Models

TL;DR

This paper introduces a new class of convexity-preserving nonconvex regularizers called pSDC, providing a unified DC programming framework for solving a broad range of nonconvex regularized convex models with proven convergence.

Contribution

It proposes the pSDC regularizer, unifies existing regularizers, and develops a less restrictive, convergent DC algorithm for solving nonconvexly regularized convex models.

Findings

pSDC regularizers effectively preserve convexity.

The proposed DC algorithm converges to a global minimizer.

Numerical experiments confirm the approach's efficiency.

Abstract

Recently, several nonconvex sparse regularizers which can preserve the convexity of the cost function have received increasing attention. This paper proposes a general class of such convexity-preserving (CP) regularizers, termed partially smoothed difference-of-convex (pSDC) regularizer. The pSDC regularizer is formulated as a structured difference-of-convex (DC) function, where the landscape of the subtrahend function can be adjusted by a parameterized smoothing function so as to attain overall-convexity. Assigned with proper building blocks, the pSDC regularizer reproduces existing CP regularizers and opens the way to a large number of promising new ones. With respect to the resultant nonconvexly regularized convex (NRC) model, we derive a series of overall-convexity conditions which naturally embrace the conditions in previous works. Moreover, we develop a unified framework based on DC programming for solving the NRC model. Compared to previously reported proximal splitting type approaches, the proposed framework makes less stringent assumptions. We establish the convergence of the proposed framework to a global minimizer. Numerical experiments demonstrate the power of the pSDC regularizers and the efficiency of the proposed DC algorithm.