Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimization

Changyou Chen, David E. Carlson, Zhe Gan, Chunyuan Li, Lawrence Carin

Abstract: Stochastic gradient Markov chain Monte Carlo (SG-MCMC) methods are Bayesian analogs to popular stochastic optimization methods; however, this connection is not well studied. We explore this relatio...