Stein’s Method for Machine Learning and Statistics
Francois-Xavier Briol · Lester Mackey · Chris Oates · Qiang Liu · Larry Goldstein · Larry Goldstein

Sat Jun 15th 08:30 AM -- 06:00 PM @ 104 A
Event URL: »

Stein's method is a technique from probability theory for bounding the distance between probability measures using differential and difference operators. Although the method was initially designed as a technique for proving central limit theorems, it has recently caught the attention of the machine learning (ML) community and has been used for a variety of practical tasks. Recent applications include generative modeling, global non-convex optimisation, variational inference, de novo sampling, constructing powerful control variates for Monte Carlo variance reduction, and measuring the quality of (approximate) Markov chain Monte Carlo algorithms. Stein's method has also been used to develop goodness-of-fit tests and was the foundational tool in one of the NeurIPS 2017 Best Paper awards.

Although Stein's method has already had significant impact in ML, most of the applications only scratch the surface of this rich area of research in probability theory. There would be significant gains to be made by encouraging both communities to interact directly, and this inaugural workshop would be an important step in this direction. More precisely, the aims are: (i) to introduce this emerging topic to the wider ML community, (ii) to highlight the wide range of existing applications in ML, and (iii) to bring together experts in Stein's method and ML researchers to discuss and explore potential further uses of Stein's method.

08:30 AM Overview of the day (Talk) Francois-Xavier Briol
08:45 AM Tutorial - Larry Goldstein: The Many Faces of a Simple Identity (Tutorial) Larry Goldstein
09:45 AM Invited Talk - Anima Anandkumar: Stein’s method for understanding optimization in neural networks. (Talk) Anima Anandkumar
10:30 AM Break <span> <a href="#"></a> </span>
11:00 AM Invited Talk - Arthur Gretton: Relative goodness-of-fit tests for models with latent variables. (Talk) Arthur Gretton
11:45 AM Invited Talk - Andrew Duncan (Talk) Andrew Duncan
12:30 PM Lunch and Poster Session (Poster)
01:45 PM Invited Talk - Yingzhen Li: Gradient estimation for implicit models with Stein's method. (Talk) Yingzhen Li
02:30 PM Invited Talk - Ruiyi Zhang: On Wasserstein Gradient Flows and Particle-Based Variational Inference (Talk) RUIYI (ROY) ZHANG
03:15 PM Break <span> <a href="#"></a> </span>
03:45 PM Invited Talk - Paul Valiant: How the Ornstein-Uhlenbeck process drives generalization for deep learning. (Talk)
04:30 PM Invited Talk - Louis Chen: Palm theory, random measures and Stein couplings. (Talk) Louis Chen
05:15 PM Panel Discussion - All speakers (Panel)

Author Information

Francois-Xavier Briol (University of Cambridge)
Lester Mackey (Microsoft Research)
Chris Oates (Newcastle University)
Qiang Liu (UT Austin)
Larry Goldstein (University of Southern California)
Larry Goldstein (University of Southern California)

More from the Same Authors