Saved in:
Bibliographic Details
Main Authors: You, Pengcheng, Liu, Yingzhu, Mallada, Enrique
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.05290
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917771551440896
author You, Pengcheng
Liu, Yingzhu
Mallada, Enrique
author_facet You, Pengcheng
Liu, Yingzhu
Mallada, Enrique
contents This work examines the conditions for asymptotic and exponential convergence of saddle flow dynamics of convex-concave functions. First, we propose an observability-based certificate for asymptotic convergence, directly bridging the gap between the invariant set in a LaSalle argument and the equilibrium set of saddle flows. This certificate generalizes conventional conditions for convergence, e.g., strict convexity-concavity, and leads to a novel state-augmentation method that requires minimal assumptions for asymptotic convergence. We also show that global exponential stability follows from strong convexity-strong concavity, providing a lower-bound estimate of the convergence rate. This insight also explains the convergence of proximal saddle flows for strongly convex-concave objective functions. Our results generalize to dynamics with projections on the vector field and have applications in solving constrained convex optimization via primal-dual methods. Based on these insights, we study four algorithms built upon different Lagrangian function transformations. We validate our work by applying these methods to solve a network flow optimization and a Lasso regression problem.
format Preprint
id arxiv_https___arxiv_org_abs_2409_05290
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Unified Analysis of Saddle Flow Dynamics: Stability and Algorithm Design
You, Pengcheng
Liu, Yingzhu
Mallada, Enrique
Optimization and Control
This work examines the conditions for asymptotic and exponential convergence of saddle flow dynamics of convex-concave functions. First, we propose an observability-based certificate for asymptotic convergence, directly bridging the gap between the invariant set in a LaSalle argument and the equilibrium set of saddle flows. This certificate generalizes conventional conditions for convergence, e.g., strict convexity-concavity, and leads to a novel state-augmentation method that requires minimal assumptions for asymptotic convergence. We also show that global exponential stability follows from strong convexity-strong concavity, providing a lower-bound estimate of the convergence rate. This insight also explains the convergence of proximal saddle flows for strongly convex-concave objective functions. Our results generalize to dynamics with projections on the vector field and have applications in solving constrained convex optimization via primal-dual methods. Based on these insights, we study four algorithms built upon different Lagrangian function transformations. We validate our work by applying these methods to solve a network flow optimization and a Lasso regression problem.
title A Unified Analysis of Saddle Flow Dynamics: Stability and Algorithm Design
topic Optimization and Control
url https://arxiv.org/abs/2409.05290