Search Results for author: Hejian Sang

Found 1 papers, 0 papers with code

Adaptive Stochastic Gradient Langevin Dynamics: Taming Convergence and Saddle Point Escape Time

no code implementations23 May 2018 Hejian Sang, Jia Liu

In this paper, we propose a new adaptive stochastic gradient Langevin dynamics (ASGLD) algorithmic framework and its two specialized versions, namely adaptive stochastic gradient (ASG) and adaptive gradient Langevin dynamics(AGLD), for non-convex optimization problems.

Cannot find the paper you are looking for? You can Submit a new open access paper.