Score: 0

Contractive kinetic Langevin samplers beyond global Lipschitz continuity

Published: September 15, 2025 | arXiv ID: 2509.12031v1

By: Iosif Lytras, Panagiotis Mertikopoulos

Potential Business Impact:

Makes computer models learn faster and more accurately.

Business Areas:
A/B Testing Data and Analytics

In this paper, we examine the problem of sampling from log-concave distributions with (possibly) superlinear gradient growth under kinetic (underdamped) Langevin algorithms. Using a carefully tailored taming scheme, we propose two novel discretizations of the kinetic Langevin SDE, and we show that they are both contractive and satisfy a log-Sobolev inequality. Building on this, we establish a series of non-asymptotic bounds in $2$-Wasserstein distance between the law reached by each algorithm and the underlying target measure.

Page Count
30 pages

Category
Mathematics:
Probability