Preprint
Oct 2026
Two-Loop Stochastic Mirror Langevin Algorithms for Constrained Sampling
A stochastic first-order version of the Mirror Langevin Algorithm (sFO-MLA) is studied and finite-time Wasserstein guarantees for sFO-MLA are established that explicitly separate mixing, Euler--Maruyama discretization, and stochastic-gradient errors.
Rui-Ting Tong, Antik Chakraborty, R. Pasupathy
· 0 citations