Bayesian learning via neural Schrödinger–Föllmer flows
Statistics and Computing · 2023-02 · 33 (1)
DOI: 10.1007/s11222-022-10172-5 ↗Kurz gefasst
Fachartikel in der Zeitschrift Statistics and Computing, online erschienen am 23.11.2022. Verfasst von Francisco Vargas und 5 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Engineering and Physical Sciences Research Council, Deutsche Forschungsgemeinschaft, Huawei Technologies.
Abstract (Originalsprache)
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.
Förderung
- Engineering and Physical Sciences Research Council
- Deutsche Forschungsgemeinschaft
- Huawei Technologies
Zitieren
APA
Vargas, F., Ovsianas, A., Fernandes, D., Girolami, M., Lawrence, N. D., & Nüsken, N. (2023). Bayesian learning via neural Schrödinger–Föllmer flows. Statistics and Computing, 33(1). https://doi.org/10.1007/s11222-022-10172-5
Vancouver
Vargas F, Ovsianas A, Fernandes D, Girolami M, Lawrence ND, Nüsken N. Bayesian learning via neural Schrödinger–Föllmer flows. Statistics and Computing. 2023;33(1). doi:10.1007/s11222-022-10172-5
BibTeX
@article{Vargas2023,
author = {Vargas, Francisco and Ovsianas, Andrius and Fernandes, David and Girolami, Mark and Lawrence, Neil D. and Nüsken, Nikolas},
title = {Bayesian learning via neural Schrödinger–Föllmer flows},
journal = {Statistics and Computing},
year = {2023},
volume = {33},
number = {1},
doi = {10.1007/s11222-022-10172-5}
}
EUVIMED