Saddle-point dynamics: conditions for asymptotic stability of saddle points

From MaRDI portal
Publication:2968544

DOI10.1137/15M1026924zbMATH Open1364.90326arXiv1510.02145OpenAlexW2962717811MaRDI QIDQ2968544FDOQ2968544


Authors: Ashish Cherukuri, Bahman Gharesifard, J. Cortés Edit this on Wikidata


Publication date: 17 March 2017

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Abstract: This paper considers continuously differentiable functions of two vector variables that have (possibly a continuum of) min-max saddle points. We study the asymptotic convergence properties of the associated saddle-point dynamics (gradient-descent in the first variable and gradient-ascent in the second one). We identify a suite of complementary conditions under which the set of saddle points is asymptotically stable under the saddle-point dynamics. Our first set of results is based on the convexity-concavity of the function defining the saddle-point dynamics to establish the convergence guarantees. For functions that do not enjoy this feature, our second set of results relies on properties of the linearization of the dynamics, the function along the proximal normals to the saddle set, and the linearity of the function in one variable. We also provide global versions of the asymptotic convergence results. Various examples illustrate our discussion.


Full work available at URL: https://arxiv.org/abs/1510.02145




Recommendations




Cites Work


Cited In (24)





This page was built for publication: Saddle-point dynamics: conditions for asymptotic stability of saddle points

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2968544)