Preprint
Oct 2026
Stochastic Gradient Leimkuhler-Matthews Integrator with Second Order Discretization Error
Stochastic gradient Langevin dynamics (SGLD) has a discretization error of first order in the step size $h$, even with the full gradient. We study the stochastic gradient Leimkuhler-Matthews (SGLM) integrator, which has the same cost as SGLD, one stochastic gradient per step, and reuses each Gaussian vector in consecut...
Xu-Da Ye, Yu-Liang Wang, Guang Lin et al.
· 0 citations