Optimization Online


A second order dynamical approach with variable damping to nonconvex smooth minimization

Radu Ioan Bot(radu.bot***at***univie.ac.at)
Ernö Robert Csetnek(ernoe.robert.csetnek***at***univie.ac.at)
Szilard Csaba Laszlo(szilard.laszlo***at***math.utcluj.ro)

Abstract: We investigate a second order dynamical system with variable damping in connection with the minimization of a nonconvex differentiable function. The dynamical system is formulated in the spirit of the differential equation which models Nesterov's accelerated convex gradient method. We show that the generated trajectory converges to a critical point, if a regularization of the objective function satisfies the Kurdyka-Lojasiewicz property. We also provide convergence rates for the trajectory formulated in terms of the Lojasiewicz exponent.

Keywords: second order dynamical system, nonconvex optimization, Kurdyka-Lojasiewicz inequality, convergence rate

Category 1: Convex and Nonsmooth Optimization (Nonsmooth Optimization )


Download: [PDF]

Entry Submitted: 05/07/2018
Entry Accepted: 05/07/2018
Entry Last Modified: 05/07/2018

Modify/Update this entry

  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository


Coordinator's Board
Classification Scheme
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society