A variable smoothing for Nonconvexly constrained nonsmooth optimization with application to sparse spectral clustering

TL;DR

This paper introduces a variable smoothing algorithm for nonconvex constrained nonsmooth optimization, transforming the problem into an unconstrained form and applying gradient descent on a smoothed approximation, with applications to sparse spectral clustering.

Contribution

It proposes a novel variable smoothing approach for nonconvex constrained nonsmooth problems, including a convergence analysis and application to sparse spectral clustering.

Findings

The algorithm converges to stationary points under certain conditions.

Effective in solving nonconvex reformulations of sparse spectral clustering.

Provides theoretical guarantees for the proposed smoothing method.

Abstract

We propose a variable smoothing algorithm for solving nonconvexly constrained nonsmooth optimization problems. The target problem has two issues that need to be addressed: (i) the nonconvex constraint and (ii) the nonsmooth term. To handle the nonconvex constraint, we translate the target problem into an unconstrained problem by parameterizing the nonconvex constraint in terms of a Euclidean space. We show that under a certain condition, these problems are equivalent in view of finding a stationary point. To find a stationary point of the parameterized problem, the proposed algorithm performs the gradient descent update for the smoothed version of the parameterized problem with replacement of the nonsmooth function by the Moreau envelope, inspired by a variable smoothing algorithm [B\"ohm-Wright, J. Optim. Theory Appl., 2021] specialized for unconstrained nonsmooth optimization. We also present a convergence analysis of the proposed algorithm as well as its application to a nonconvex reformulation of the sparse spectral clustering.