2000 character limit reached
Stochastic Gradient Langevin Dynamics with Variance Reduction (2102.06759v1)
Published 12 Feb 2021 in cs.LG and math.OC
Abstract: Stochastic gradient Langevin dynamics (SGLD) has gained the attention of optimization researchers due to its global optimization properties. This paper proves an improved convergence property to local minimizers of nonconvex objective functions using SGLD accelerated by variance reductions. Moreover, we prove an ergodicity property of the SGLD scheme, which gives insights on its potential to find global minimizers of nonconvex objectives.