Optimal-Transport Bayesian Sampling in the Era of Deep Learning

Applied and Computational Mathematics Seminar
Monday, August 24, 2020 - 2:00pm for 1 hour (actually 50 minutes)
Bluejeans (online) https://bluejeans.com/197711728
Prof. Changyou Chen – University at Buffalo
Molei Tao

Deep learning has achieved great success in recent years. One aspect overlooked by traditional deep-learning methods is uncertainty modeling, which can be very important in certain applications such as medical image classification and reinforcement learning. A standard way for uncertainty modeling is by adopting Bayesian inference. In this talk, I will share some of our recent work on scalable Bayesian inference by sampling, called optimal-transport sampling, motivated from the optimal-transport theory. Our framework formulates Bayesian sampling as optimizing a set of particles, overcoming some intrinsic issues of standard Bayesian sampling algorithms such as sampling efficiency and algorithm scalability. I will also describe how our sampling framework be applied to uncertainty and repulsive attention modeling in state-of-the-art natural-language-processing models.