Back to Search Start Over

Bayesian Learning via Neural Schr\'odinger-F\'ollmer Flows

Authors :
Vargas, Francisco
Ovsianas, Andrius
Fernandes, David
Girolami, Mark
Lawrence, Neil D.
Nüsken, Nikolas
Publication Year :
2021

Abstract

In this work we explore a new framework for approximate Bayesian inference in large datasets based on stochastic control (i.e. Schr\"odinger bridges). We advocate stochastic control as a finite time and low variance alternative to popular steady-state methods such as stochastic gradient Langevin dynamics (SGLD). Furthermore, we discuss and adapt the existing theoretical guarantees of this framework and establish connections to already existing VI routines in SDE-based models.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2111.10510
Document Type :
Working Paper