A fast continuous time approach with time scaling for nonsmooth convex optimization

TL;DR

This paper introduces a novel second-order dynamical system with time scaling for nonsmooth convex optimization, achieving fast convergence rates and weak convergence to a global minimizer, supported by theoretical analysis and numerical experiments.

Contribution

It develops a new continuous-time approach combining viscous and Hessian-driven damping with time scaling for nonsmooth convex functions, providing convergence guarantees and numerical validation.

Findings

Fast convergence rates for the Moreau envelope and its gradient.

Weak convergence of the system trajectory to a global minimizer.

Numerical examples confirming theoretical results.

Abstract

In a Hilbert setting we study the convergence properties of a second order in time dynamical system combining viscous and Hessian-driven damping with time scaling in relation with the minimization of a nonsmooth and convex function. The system is formulated in terms of the gradient of the Moreau envelope of the objective function with time-dependent parameter. We show fast convergence rates for the Moreau envelope and its gradient along the trajectory, and also for the velocity of the system. From here we derive fast convergence rates for the objective function along a path which is the image of the trajectory of the system through the proximal operator of the first. Moreover, we prove the weak convergence of the trajectory of the system to a global minimizer of the objective function. Finally, we provide multiple numerical examples which illustrate the theoretical results.