Deep generative models and Schrödinger Bridge

Deep generative models have achieved enormous success in learning the underlying high-dimensional data distribution from samples. In this talk, we will introduce two methods to learn deep generative models. First, we will introduce variational gradient flow (VGrow) which can be used to minimize the f-divergence between the evolving distribution and the target distribution. In particular, we showed that the commonly used logD-trick indeed belongs to f-divergence. Second, we will introduce a Schrödinger Bridge approach to learning deep generative models. Our theoretical results guarantee that the distribution learned by our approach converges to the target distribution. Experimental results on multimodal synthetic data and benchmark data support our theoretical findings and indicate that the generative model via Schrödinger Bridge is comparable with state-of-the-art GANs, suggesting a new formulation of generative learning. We demonstrate its usefulness in image interpolation and image inpainting.

Biography

Professor Yang Wang took office as Vice-President for Institutional Advancement of the Hong Kong University of Science and Technology (HKUST) on 1 October 2020. He is also a Chair Professor of Mathematics. He joined the HKUST as the Head of the Department of Mathematics in 2014 and he became the Dean of School of Science in 2016.

Professor Wang is an internationally respected scholar with wide ranging research interests, having published over 100 research journal papers in both pure and interdisciplinary mathematics, many of which in top journals. During his tenure as Dean of Science and Head of Mathematics, Prof Wang founded the HKUST Big Data Institute and launched the popular Big Data Technology MSc program.

Professor Wang received his Bachelor degree in Mathematics from the University of Science and Technology of China in 1983 and obtained his PhD degree in Mathematics from Harvard University in 1990. He started his academic career with the Georgia Institute of Technology in 1989 and then moved on to be the Department Chair and Professor of Mathematics at Michigan State University in 2007. He was also a Program Director at the National Science Foundation between 2006 and 2007.