Bayesian Learning via Neural Schrödinger-Föllmer Flows

2021/11/20 by Francisco Vargas, Andrius Ovsianas, Vargas, Francisco +9 · 6 citations
Computer Science · Physics and Astronomy · #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Model Reduction and Neural Networks #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.2111.10510

openalex publication_date 2021/11/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this work we explore a new framework for approximate Bayesian inference in large datasets based on stochastic control (i.e. Schrödinger 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.

Cited by

• Functional Adjoint Sampler: Scalable Sampling on Infinite Dimensional Spaces
• Meta Flow Maps enable scalable reward alignment
• Reinforced sequential Monte Carlo for amortised sampling
• Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference
• MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control
• Path Integral Optimiser: Global Optimisation via Neural Schrödinger-Föllmer Diffusion

Related

• A kernel-based method for Schrödinger bridges
• Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions
• Stochastic Normalizing Flows
• A Closed-Form Framework for Schrödinger Bridges Between Arbitrary Densities
• Soft-constrained Schrodinger Bridge: a Stochastic Control Approach