A note on uniform in time mean-field limit in graphs
Pierre Le Bris, Christophe Poquet

TL;DR
This paper demonstrates uniform in time propagation of chaos for particle systems on graphs with Lipschitz interactions, using reflection coupling, and provides bounds depending on the graph structure.
Contribution
It extends mean-field limit results to non-exchangeable particle systems on dense graphs with non-convex potentials, using a reflection coupling approach.
Findings
Uniform in time propagation of chaos established.
Explicit bounds depending on graph density derived.
Applicable to systems with non-convex confining potentials.
Abstract
In this article we show, in a concise manner, a result of uniform in time propagation of chaos for non exchangeable systems of particles interacting according to a random graph. Provided the interaction is Lipschitz continuous, the restoring force satisfies a general one-sided Lipschitz condition (thus allowing for non-convex confining potential) and the graph is dense enough, we use a coupling method suggested by Eberle known as reflection coupling to obtain uniform in time mean-field limit with bounds that depend explicitly on the graph structure.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsQuantum chaos and dynamical systems · stochastic dynamics and bifurcation · Theoretical and Computational Physics
