English

Approaching nonsmooth nonconvex optimization problems through first order dynamical systems with hidden acceleration and Hessian driven damping terms

Optimization and Control 2016-10-05 v1 Dynamical Systems

Abstract

In this paper we carry out an asymptotic analysis of the proximal-gradient dynamical system \begin{equation*}\left\{ \begin{array}{ll} \dot x(t) +x(t) = \prox_{\gamma f}\big[x(t)-\gamma\nabla\Phi(x(t))-ax(t)-by(t)\big],\\ \dot y(t)+ax(t)+by(t)=0 \end{array}\right.\end{equation*} where ff is a proper, convex and lower semicontinuous function, Φ\Phi a possibly nonconvex smooth function and γ,a\gamma, a and bb are positive real numbers. We show that the generated trajectories approach the set of critical points of f+Φf+\Phi, here understood as zeros of its limiting subdifferential, under the premise that a regularization of this sum function satisfies the Kurdyka-\L{}ojasiewicz property. We also establish convergence rates for the trajectories, formulated in terms of the \L{}ojasiewicz exponent of the considered regularization function.

Keywords

Cite

@article{arxiv.1610.00911,
  title  = {Approaching nonsmooth nonconvex optimization problems through first order dynamical systems with hidden acceleration and Hessian driven damping terms},
  author = {Radu Ioan Bot and Ernö Robert Csetnek},
  journal= {arXiv preprint arXiv:1610.00911},
  year   = {2016}
}

Comments

arXiv admin note: substantial text overlap with arXiv:1507.01416

R2 v1 2026-06-22T16:09:52.101Z