Saddle Flow Dynamics: Observable Certificates and Separable Regularization

arXiv2009.14714MaRDI QIDQ6350243FDOQ6350243

Authors: Pengcheng You, Enrique Mallada 

Publication date: 30 September 2020

Abstract: This paper proposes a certificate, rooted in observability, for asymptotic convergence of saddle flow dynamics of convex-concave functions to a saddle point. This observable certificate directly bridges the gap between the invariant set and the equilibrium set in a LaSalle argument, and generalizes conventional conditions such as strict convexity-concavity and proximal regularization. We further build upon this certificate to propose a separable regularization method for saddle flow dynamics that makes minimal requirements on convexity-concavity and yet still guarantees asymptotic convergence to a saddle point. Our results generalize to saddle flow dynamics with projections on the vector field and have an immediate application as a distributed solution to linear programs.

This page was built for publication: Saddle Flow Dynamics: Observable Certificates and Separable Regularization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6350243)