On cutoff via rigidity for high dimensional curved diffusions
Djalil Chafa\"i, Max Fathi

TL;DR
This paper demonstrates a cutoff phenomenon in high-dimensional curved diffusions, including non-Gaussian cases, at a critical time related to the spectral gap, using functional inequalities and spectral rigidity concepts.
Contribution
It establishes the occurrence of cutoff in high-dimensional curved diffusions at a specific time, extending the understanding beyond Gaussian cases with new spectral and functional inequality techniques.
Findings
Cutoff occurs at time log(dimension)/(2 * spectral gap)
Cutoff holds across Wasserstein, total variation, entropy, and Fisher information
Extension to Riemannian manifolds and new curvature product condition introduced
Abstract
We consider overdamped Langevin diffusions in Euclidean space, with curvature equal to the spectral gap. This includes the Ornstein-Uhlenbeck process as well as non-Gaussian and non-product extensions with convex interaction, such as the Dyson process from random matrix theory. We show that a cutoff phenomenon or abrupt convergence to equilibrium occurs in high dimension, at a critical time equal to the logarithm of the dimension divided by twice the spectral gap. This cutoff holds for Wasserstein distance, total variation, relative entropy, and Fisher information. A key observation is a relation to a spectral rigidity, linked to the presence of a Gaussian factor. A novelty is the extensive usage of functional inequalities, even for short-time regularization, and the reduction to Wasserstein. The proofs are short and conceptual. Since the product condition is satisfied, an Lp cutoff…
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.
Taxonomy
TopicsTopological and Geometric Data Analysis · Markov Chains and Monte Carlo Methods · Statistical Mechanics and Entropy
