Bayesian learning via neural Schrödinger–Föllmer flows

Francisco Vargas; Andrius Ovsianas; David Fernandes; Mark Girolami; Neil D. Lawrence; Nikolas Nüsken

doi:10.1007/s11222-022-10172-5

edit

Back to publications

Bayesian learning via neural Schrödinger–Föllmer flows

Francisco Vargas, Andrius Ovsianas, David Fernandes, Mark Girolami, Neil D. Lawrence, Nikolas Nüsken

, 33(3), 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.

Links

Cite this Paper

BibTeX


@Article{bayesian-learning-via-schroedinger-follmer-flows,
  title = 	 {Bayesian learning via neural Schrödinger–Föllmer flows},
  author = 	 {Vargas, Francisco and Ovsianas, Andrius and Fernandes, David and Girolami, Mark and Lawrence, Neil D. and Nüsken, Nikolas},
  year = 	 {2022},
  volume = 	 {33},
  number =       {3},
  doi = 	 {10.1007/s11222-022-10172-5},
  pdf = 	 {https://trebuchet.public.springernature.app/get_content/f9636384-d26a-4b40-bd96-3adb08e2c867},
  url = 	 {/publications/bayesian-learning-via-schroedinger-follmer-flows.html},
  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.}
}

Endnote

%0 Journal Article
%T Bayesian learning via neural Schrödinger–Föllmer flows
%A Francisco Vargas
%A Andrius Ovsianas
%A David Fernandes
%A Mark Girolami
%A Neil D. Lawrence
%A Nikolas Nüsken
%D 2022	
%F bayesian-learning-via-schroedinger-follmer-flows
%R 10.1007/s11222-022-10172-5
%U /publications/bayesian-learning-via-schroedinger-follmer-flows.html
%V 33
%N 3
%X 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.

RIS


TY  - JOUR
TI  - Bayesian learning via neural Schrödinger–Föllmer flows
AU  - Francisco Vargas
AU  - Andrius Ovsianas
AU  - David Fernandes
AU  - Mark Girolami
AU  - Neil D. Lawrence
AU  - Nikolas Nüsken
BT  - Statistics and Computing
DA  - 2022/11/23	
ID  - bayesian-learning-via-schroedinger-follmer-flows
VL  - 33
IS  - 3
DO  - 10.1007/s11222-022-10172-5
L1  - https://trebuchet.public.springernature.app/get_content/f9636384-d26a-4b40-bd96-3adb08e2c867
UR  - /publications/bayesian-learning-via-schroedinger-follmer-flows.html
AB  - 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.
ER  -

APA


Vargas, F., Ovsianas, A., Fernandes, D., Girolami, M., Lawrence, N.D. & Nüsken, N.. (2022). Bayesian learning via neural Schrödinger–Föllmer flows.  33(3) doi:10.1007/s11222-022-10172-5 Available from /publications/bayesian-learning-via-schroedinger-follmer-flows.html.