Wasserstein mixing time of the unadjusted Langevin algorithm

arXiv:2608.02430v1 Announce Type: cross Abstract: We provide new estimates in Wasserstein distance for the asymptotic bias of the unadjusted Langevin algorithm, in the classical setting of log-smooth strongly log-concave measures. Our bound implies a Wasserstein mixing time of order kappa sqrt{d}/arepsilon, where kappa is the condition number, d is the dimension, and arepsilon is the target precision: this improves by a factor of sqrt{d}/arepsilon over the previous state-of-the-art results.

Source: arXiv cs.LG | 2026-08-04