Stein Point Markov Chain Monte Carlo
Wilson Ye Chen · Alessandro Barp · Francois-Xavier Briol · Jackson Gorham · Mark Girolami · Lester Mackey · Chris Oates

Tue Jun 11th 12:00 -- 12:05 PM @ Room 101

An important task in machine learning and statistics is the approximation of a probability measure by an empirical measure supported on a discrete point set. Stein Points are a class of algorithms for this task, which proceed by sequentially minimising a Stein discrepancy between the empirical measure and the target and, hence, require the solution of a non-convex optimisation problem to obtain each new point. This paper removes the need to solve this optimisation problem by, instead, selecting each new point based on a Markov chain sample path. This significantly reduces the computational cost of Stein Points and leads to a suite of algorithms that are straightforward to implement. The new algorithms are illustrated on a set of challenging Bayesian inference problems, and rigorous theoretical guarantees of consistency are established.

Author Information

Wilson Ye Chen (The Institute of Statistical Mathematics)
Alessandro Barp (Imperial College London)
Francois-Xavier Briol (University of Cambridge)
Jackson Gorham (OPENDOOR)
Mark Girolami (Imperial College London)
Lester Mackey (Microsoft Research)
Chris Oates (Newcastle University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors