Skip to yearly menu bar Skip to main content


Poster

Score Operator Newton transport

Nisha Chandramoorthy · Florian Schaefer · Youssef Marzouk

MR1 & MR2 - Number 154
[ ]
Sat 4 May 6 a.m. PDT — 8:30 a.m. PDT

Abstract:

We propose a new approach for sampling and Bayesian computation that uses the score of the target distribution to construct a transport from a given reference distribution to the target. Our approach is an infinite-dimensional Newton method, involving an elliptic PDE, for finding a zero of a ``score-residual'' operator. We prove sufficient conditions for convergence to a valid transport map. Our Newton iterates can be computed by exploiting fast solvers for elliptic PDEs, resulting in new algorithms for Bayesian inference and other sampling tasks. We identify elementary settings where score-operator Newton transport achieves fast convergence while avoiding mode collapse.

Live content is unavailable. Log in and register to view live content