Quantitative approximate independence for continuous mean field Gibbs measures

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 n → ∞ 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) c∧2 ), 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.

Hierarchies, entropy, and quantitative propagation of chaos for mean field diffusions

“…The first result, Proposition 7.1, is nearly covered by existing results, with the exception that b 0 is not required to be bounded. Our proof is inspired by the approach of [43,Theorem 2.4]. As usual, we assume implicitly that b 0 and b are progressively measurable.…”

“…Relative entropy methods appear to be more recent in the analysis of mean field limits. As discussed above, prior work [34,36,37,43,49] has focused on establishing global entropy estimates like (1.9), with local estimates like (1.11) deduced from subadditivity. The main novelty of our approach is to develop local relative entropy estimates, which allow us to improve (1.11) to (1.5).…”