【Academic Seminar】Stein Neural Sampler - Prof. Guang Cheng

Topic: Stein Neural Sampler

Speaker: Prof. Guang Cheng, Purdue University

Date and Time: 10:30 am - 11:30 am, Monday, July 8, 2019

Venue: Room 103, Cheng Dao Building

Abstract：

We propose two novel sampling methods to generate high-quality samples from a given (un-normalized) probability density. Motivated by the success of generative adversarial networks (GAN), we construct our samplers using neural networks that transform a reference distribution to the target distribution. Training schemes are developed to minimize two variations of Stein discrepancy, which is designed to work with un-normalized densities. Once trained, our samplers are able to generate independent samples instantaneously. We show that the proposed methods are theoretically sound and experience fewer convergence issues compared with traditional sampling approaches according to our empirical studies.

Biography：

Guang Cheng is a Professor of Statistics at Purdue University. He received his PhD in Statistics from University of Wisconsin-Madison in 2006. His research interests include Big Data and High Dimensional Statistical Inferences, and more recently turn to Deep Learning and Reinforcement Learning. Cheng is the recipient of the NSF CAREER award, Noether Young Scholar Award and Simons Fellowship in Mathematics. He will be a visiting member of Institute of Advanced Study, Princeton in the fall of 2019. Please visit his big data theory research group at http://www.science.purdue.edu/bigdata/.