
TL;DR
This paper introduces a novel method for constructing Stein kernels via moment maps, linking geometric solutions to the Monge-Ampère equation with convergence rates in the central limit theorem, especially for log-concave measures.
Contribution
It presents a new approach to Stein kernels using moment maps and establishes explicit convergence rates in Wasserstein distance for log-concave distributions.
Findings
Regularity bounds on moment maps control convergence rates.
Derived new polynomial dimension-dependent rates in Wasserstein distance.
Applied to log-concave measures for improved CLT convergence estimates.
Abstract
We describe a construction of Stein kernels using moment maps, which are solutions to a variant of the Monge-Amp\`ere equation. As a consequence, we show how regularity bounds on these maps control the rate of convergence in the classical central limit theorem, and derive new rates in Kantorovitch-Wasserstein distance in the log-concave situation, with explicit polynomial dependence on the dimension.
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.
