16 citations · 16 across the 2 of their papers we have counts for
2 papers
stat.ML2020★ 16 cited
Accelerating Nonconvex Learning via Replica Exchange Langevin Diffusion
Yi Chen, Jinglin Chen, Jing Dong +2
Langevin diffusion is a powerful method for nonconvex optimization, which enables the escape from local minima by injecting noise into the gradient. In particular, the temperature…
math.PR2016
Exact Sampling of the Infinite Horizon Maximum of a Random Walk Over a Non-linear Boundary
Jose Blanchet, Jing Dong, Zhipeng Liu
We present the first algorithm that samples where is a mean zero random walk, and with defines a nonliner boundary. We show…