Saved in:
Bibliographic Details
Main Authors: Maulén, Juan José, Guo, Huiyuan, Peypouquet, Juan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.11267
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • We introduce a new restarting scheme for a continuous inertial dynamics with Hessian driven-damping, and establish a linear convergence rate for the function values along the restarted trajectories. The proposed routine is implemented without knowing the strong convexity parameter, and is a generalization of existing speed restart schemes. It interpolates between speed and function value restarts, considerably delaying the restarting time, while preserving convergence and function value decrease. Numerical experiments show an improvement in the convergence rates for both continuous-time dynamical systems, and the associated accelerated first-order algorithms derived via time discretization.