Non-exchangeable mean-field theory for adaptive weights: propagation of dissociatedness and graphon sampling lemma

2025/06/16 by Datong P. Zhou, Zhou, Datong
Economics, Econometrics and Finance · #05C22 #05C80 #49Q22 #60G57 #60H10 #60K35 #62D05 #Analysis of PDEs (math.AP) #Combinatorics (math.CO) #FOS: Mathematics #Probability (math.PR) #Stochastic processes and financial applications

paper · pdf · doi:10.48550/arxiv.2506.13587

openalex publication_date 2025/06/16 · openalex created_date 2025/10/13 · openalex updated_date 2026/07/31

Abstract

We develop a mean-field theory for large, non-exchangeable particle (agent) systems where the states and interaction weights co-evolve in a coupled system of SDEs. A first main result is the establishment of the propagation of dissociatedness, a conceptual generalization of the classical propagation of chaos that accommodates the intrinsic local correlations between particles and their weights. The limiting McKean-Vlasov process is characterized by an Aldous-Hoover representation on a filtered probability space, beyond the standard one-particle law (or a family thereof). Paralleling the classical equivalence between propagation of chaos and the convergence of empirical measures to the one-particle law, we show that the propagation of dissociatedness corresponds to the convergence of the empirical structure under a distance unifying the Wasserstein distance for particles and the cut distance for weights. This quantitative stability is grounded in an adaptation of the sampling lemma from dense graph theory, analogous to the classical concentration results for empirical measures in the Wasserstein distance.

Citations

• Mean-Field Analysis of Latent Variable Process Models on Dynamically Evolving Graphs with Feedback Effects
• Uniform-in-time propagation of chaos for the Cucker--Smale model
• Coupling and Tensorization of Kinetic Theory and Graph Theory
• Interacting particle systems on sparse W-random graphs
• Mean-field limit of non-exchangeable multi-agent systems over hypergraphs with unbounded rank
• Nonlinear Graphon mean-field systems
• Large-population limits of non-exchangeable particle systems
• The graph limit for a pairwise competition model
• The mean-field Limit of sparse networks of integrate and fire neurons
• Graphon-valued processes with vertex-level fluctuations
• Vlasov Equations on Directed Hypergraph Measures
• A label-state formulation of stochastic graphon games and approximate equilibria on large networks
• Mean-field limit of non-exchangeable systems
• Continuum Limits for Adaptive Network Dynamics
• Vlasov equations on digraph measures
• Stochastic Graphon Games: II. The Linear-Quadratic Case
• Graph Similarity and Homomorphism Densities
• Mean-field and graph limits for collective dynamics models with time-varying weights
• Graphon Mean Field Games and Their Equations
• Graphop Mean-Field Limits for Kuramoto-Type Models
• Graphon mean field systems
• Graphon mean field systems
• Mean field interaction on random graphs with dynamically changing multi-color edges
• Stochastic Graphon Games: I. The Static Case
• Fractional Isomorphism of Graphons
• Graphon-valued stochastic processes from population genetics
• Action convergence of operators and graphs
• Markovian dynamics of exchangeable arrays
• Mathematical models of collective dynamics and self-organization
• On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport
• Lovász Meets Weisfeiler and Leman
• The mean field equation for the Kuramoto model on graph sequences with\n non-Lipschitz limit
• The mean field analysis for the Kuramoto model on graphs I. The mean field equation and transition point formulas
• Continuum dynamics of the intention field under weakly cohesive social interactions
• Dynamic network models and graphon estimation
• On a toy model of interacting neurons
• Analysis of Nonlinear Noisy Integrate&Fire Neuron Models: blow-up and steady states
• Graph limits and exchangeable random graphs
• Convergent Sequences of Dense Graphs I: Subgraph Frequencies, Metric Properties and Testing
• The exact law of large numbers via Fubini extension and characterization of insurable risks

Related

• The mean-field limit of non-exchangeable particle systems with non-conservative dynamics and adaptive weights
• Mean-field limits à la Tanaka and large deviations for particle systems with network interactions
• Quantitative propagation of chaos for non-exchangeable diffusions via first-passage percolation
• Coupling and Tensorization of Kinetic Theory and Graph Theory
• Nonlinear Graphon mean-field systems