Approximate independence of typical marginals of high-dimensional probability measures
math.PR
Submitted: 2026-11-05
Updated: 2026-11-05
License: http://creativecommons.org/licenses/by/4.0/
The gist: For many probability measures on R n, and for k sufficiently smaller than n, most k-dimensional coordinate marginals are close to product measures.
Abstract
For many probability measures on R n, and for k sufficiently smaller than n, most k-dimensional coordinate marginals are close to product measures. We prove this in two regimes, which notably involve no exchangeability assumptions as in prior theorems of de Finetti type. First, for log-concave measures, the quantitative bound depends on the measure only through the operator norm of its correlation matrix, and k may grow polynomially with n. A key ingredient of the proof is a new strengthening of the subadditivity of relative entropy for strongly log-concave measures, which as a byproduct yields sharp bounds in the strongly log-concave case. Second, for a broad class of measures satisfying just a variance inequality much weaker than Poincaré's, k must stay below the sharp threshold 2 n/ n. Here the basis of R n is fixed a priori, which makes this phenomenon quite different from known Gaussian approximations for low-dimensional projections such as the central limit theorem for convex bodies, although there are remarkable parallels. Insofar as Gaussian approximations are driven by the thin shell property, our results are driven by variance inequalities for additive functions which have appeared in the literature on the Gibbs sampler.
Sources
- Entropy contraction of the Gibbs sampler under log-concavity
- Operator Norm Bounds on the Correlation Matrix of the SK Model at High Temperature
- Digesting the proof of the sharp thin-shell inequality
- The total variation distance between high-dimensional Gaussians with the same mean
- Dynamical mean-field analysis of adaptive Langevin diffusions: Replica-symmetric fixed point and empirical Bayes
- A note on Bourgain's slicing problem
- The Optimal Rate in the Averaged Random-Marginal Central Limit Theorem for Log-Concave Measures
- Thin-shell bounds via parallel coupling
- Quantitative propagation of chaos for non-exchangeable diffusions via first-passage percolation
- High-Temperature Increasing Propagation of Chaos and its breakdown for the Hopfield Model
- A Mean Field Approach to Empirical Bayes Estimation in High-dimensional Linear Regression
- Dynamical mean-field analysis of adaptive Langevin diffusions: Propagation-of-chaos and convergence of the linear response
Related papers
- Rank-One HCIZ Integrals and Multiplicative Convolutions
- Repeated averaging on random d-regular graphs
- Precise cover times for branching random walks on Hamming graphs: (iterated) logarithmic corrections
- Markov Chain CLTs: Resolving Open Problems
- Marked stable L'evy processes in Brownian local time
- A Sharp Refinement of Samuels' Inequality via Cap Moves