Bayesian learning via neural Schrödinger–Föllmer flows
Francisco Vargas, Andrius Ovsianas, David Fernandes, Mark Girolami, Neil David Lawrence, Nikolas Nüsken · Statistics and Computing · 2022
Abstract In 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.