Repository logo
 

Solving Schrödinger Bridges via Maximum Likelihood.

Published version
Peer-reviewed

Type

Article

Change log

Abstract

The Schrödinger bridge problem (SBP) finds the most likely stochastic evolution between two probability distributions given a prior stochastic evolution. As well as applications in the natural sciences, problems of this kind have important applications in machine learning such as dataset alignment and hypothesis testing. Whilst the theory behind this problem is relatively mature, scalable numerical recipes to estimate the Schrödinger bridge remain an active area of research. Our main contribution is the proof of equivalence between solving the SBP and an autoregressive maximum likelihood estimation objective. This formulation circumvents many of the challenges of density estimation and enables direct application of successful machine learning techniques. We propose a numerical procedure to estimate SBPs using Gaussian process and demonstrate the practical usage of our approach in numerical simulations and experiments.

Description

Keywords

Schrödinger bridges, machine learning, stochastic control

Journal Title

Entropy (Basel)

Conference Name

Journal ISSN

1099-4300
1099-4300

Volume Title

23

Publisher

MDPI AG
Sponsorship
Engineering and Physical Sciences Research Council (EP/P034616/1)
EPSRC (EP/T517847/1)