Mathematical Programming

, Volume 116, Issue 1, pp 5–16

On the convergence of the proximal algorithm for nonsmooth functions involving analytic features

Authors

    • I3M UMR CNRS 5149Université Montpellier II
  • Jérôme Bolte
    • Equipe Combinatoire et Optimisation (UMR 7090), Case 189Université Pierre et Marie Curie
FULL LENGTH PAPER

DOI: 10.1007/s10107-007-0133-5

Cite this article as:
Attouch, H. & Bolte, J. Math. Program. (2009) 116: 5. doi:10.1007/s10107-007-0133-5

Abstract

We study the convergence of the proximal algorithm applied to nonsmooth functions that satisfy the Łjasiewicz inequality around their generalized critical points. Typical examples of functions complying with these conditions are continuous semialgebraic or subanalytic functions. Following Łjasiewicz’s original idea, we prove that any bounded sequence generated by the proximal algorithm converges to some generalized critical point. We also obtain convergence rate results which are related to the flatness of the function by means of Łjasiewicz exponents. Apart from the sharp and elliptic cases which yield finite or geometric convergence, the decay estimates that are derived are of the type O(ks), where s ∈ (0, + ∞) depends on the flatness of the function.

Keywords

Proximal algorithmŁjasiewicz inequalitySubanalytic functions

Mathematics Subject Classification (2000)

90C2647N1090C30

Copyright information

© Springer-Verlag 2007