Stein optimal transport for Bayesian inference

Nikolas Nuesken (KCL, London)

May 17. 2022, 11:45 — 12:30

This talk is about Stein optimal transport, a methodology for Bayesian inference that pushes an ensemble of particles along a predefined curve of tempered probability distributions. The driving vector field is chosen from a reproducing kernel Hilbert space and can equivalently be obtained from either a suitable kernel ridge regression formulation or as an infinitesimal optimal transport map. The update equations of Stein-OT resemble those of Stein variational gradient descent (SVGD), but introduce a time-varying score function as well as specific weights attached to the particles. I will discuss the geometric underpinnings of Stein-OT and SVGD, and Ð time permitting - connections to MCMC and the theory of large deviations.

Further Information
Venue:
ESI Boltzmann Lecture Hall
Associated Event:
Computational Uncertainty Quantification: Mathematical Foundations, Methodology & Data (Thematic Programme)
Organizer(s):
Clemens Heitzinger (TU Vienna)
Fabio Nobile (EPFL Lausanne)
Robert Scheichl (U Heidelberg)
Christoph Schwab (ETH Zürich)
Sara van de Geer (ETH Zürich)
Karen Willcox (U of Texas, Austin)