Back to publications
Bayesian learning via neural Schrödinger–Föllmer flows
Paper Details
Published: 2022/11/23
Journal: Statistics and Computing
Volume: 33
Number: 3
DOI: 10.1007/s11222-022-10172-5
Paper Links
HTMLIn this work we explore a new framework for approximate Bayesian inference in large datasets based on stochastic control. We advocate stochastic control as a finite time and low variance alternative to popular steady-state methods such as stochastic gradient Langevin dynamics. Furthermore, we discuss and adapt the existing theoretical guarantees of this framework and establish connections to already existing VI routines in SDE-based models.
Authors
Francisco Vargas
Andrius Ovsianas
David Fernandes
Mark Girolami