Saddle Flow Dynamics: Observable Certificates and Separable Regularization
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.
Keywords
Cite
@article{arxiv.2009.14714,
title = {Saddle Flow Dynamics: Observable Certificates and Separable Regularization},
author = {Pengcheng You and Enrique Mallada},
journal= {arXiv preprint arXiv:2009.14714},
year = {2020}
}