Quantitative approximate independence for continuous mean field Gibbs measures

DOI10.1214/22-EJP743MaRDI QIDQ2076648zbMATH OpenOpenAlexFDO

Authors Daniel Lacker

Publication date 22 February 2022

Published in Electronic Journal of Probability (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2105.03238

zbMATH Keywords

Fisher informationGibbs measuresmean field limitpropagation of chaosrelative entropy

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Continuum models (systems of particles, etc.) arising in equilibrium statistical mechanics (82B21)

Abstract: Many Gibbs measures with mean field interactions are known to be chaotic, in the sense that any collection of $k$ particles in the $n$-particle system are asymptotically independent, as $noinfty$ with $k$ fixed or perhaps $k=o(n)$. This paper quantifies this notion for a class of continuous Gibbs measures on Euclidean space with pairwise interactions, with main examples being systems governed by convex interactions and uniformly convex confinement potentials. The distance between the marginal law of $k$ particles and its limiting product measure is shown to be $O((k/n{)}^{cwedge2})$, with $c$ proportional to the squared temperature. In the high temperature case, this improves upon prior results based on subadditivity of entropy, which yield $O(k/n)$ at best. The bound $O((k/n{)}^2)$ cannot be improved, as a Gaussian example demonstrates. The results are non-asymptotic, and distance is quantified via relative Fisher information, relative entropy, or the squared quadratic Wasserstein metric. The method relies on an a priori functional inequality for the limiting measure, used to derive an estimate for the $k$-particle distance in terms of the $(k+1)$-particle distance.

Recommendations

• Increasing propagation of chaos for mean field models
• Hierarchies, entropy, and quantitative propagation of chaos for mean field diffusions
• scientific article; zbMATH DE number 3876374
• Large deviations for empirical measures of mean-field Gibbs measures
• Gibbs measures of continuous systems: an analytic approach

Cites work

• A dozen de Finetti-style results in search of a theory
• A large deviation principle for empirical measures on Polish spaces: application to singular Gibbs measures on manifolds
• A new characterization of quadratic transportation-information inequalities
• An elementary approach to uniform in time propagation of chaos
• Analysis and approximation of rare events. Representations and weak convergence methods
• Analysis and geometry of Markov diffusion operators
• Approximate independence of distributions on spheres and their stability properties
• Conditional limit theorems for exponential families and finite versions of de Finetti's theorem
• Convergence to equilibrium for granular media equations and their Euler schemes
• Entropic CLT and phase transition in high-dimensional Wishart matrices
• Entropy and chaos in the Kac model
• Finite exchangeable sequences
• First-order global asymptotics for confined particles with singular pair repulsion
• Genealogies and increasing propagation of chaos for Feynman-Kac and genetic models.
• Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
• scientific article; zbMATH DE number 3121490 (Why is no real title available?)
• scientific article; zbMATH DE number 4211245 (Why is no real title available?)
• scientific article; zbMATH DE number 27019 (Why is no real title available?)
• scientific article; zbMATH DE number 219860 (Why is no real title available?)
• scientific article; zbMATH DE number 3894218 (Why is no real title available?)
• Increasing propagation of chaos for mean field models
• Kinetic equilibration rates for granular media and related equations: entropy dissipation and mass transportation estimates
• Large deviations for configurations generated by Gibbs distributions with energy functionals consisting of singular interaction and weakly confining potentials
• Large deviations for empirical measures of mean-field Gibbs measures
• Log-concavity and strong log-concavity: a review
• Logarithmic Sobolev inequalities for some nonlinear PDE's.
• Mean field limit and propagation of chaos for Vlasov systems with bounded forces
• Nonlinear self-stabilizing processes. I: Existence, invariant probability, propagation of chaos
• On Kac's chaos and related problems
• On the rate of convergence in Wasserstein distance of the empirical measure
• Probabilistic approach for granular media equations in the non-uniformly convex case
• Projecting the surface measure of the sphere of \({\ell}_p^n\)
• Quantitative estimates of propagation of chaos for stochastic systems with \(W^{-1,\infty}\) kernels
• Séminaire de Probabilités XXXVI
• The Frechet distance between multivariate normal distributions
• Transportation-information inequalities for Markov processes

Cited in

(7)

• The structure of low-complexity Gibbs measures on product spaces
• Stationary solutions and local equations for interacting diffusions on regular trees
• scientific article; zbMATH DE number 889965 (Why is no real title available?)
• Sharp uniform-in-time propagation of chaos
• Phase transitions, logarithmic Sobolev inequalities, and uniform-in-time propagation of chaos for weakly interacting diffusions
• Mean field approximations via log-concavity
• Modulated logarithmic Sobolev inequalities and generation of chaos

This page was built for publication: Quantitative approximate independence for continuous mean field Gibbs measures

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2076648)