Learning minimal representations of stochastic processes with variational autoencoders
Physical Review E · 18.07.2024 · 110 (1)
DOI: 10.1103/physreve.110.l012102 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physical Review E, online erschienen am 18.07.2024. Verfasst von Gabriel Fernández-Fernández und 4 weiteren Autor:innen. Beteiligte Einrichtung: ICFO-Institut de Ciències Fotòniques, The Barcelona Institute of Science and Technology, Av. Carl Friedrich Gauss 3, 08860 Castelldefels (Barcelona),…. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: European Commission, Ministerio de Ciencia e Innovación, Generalitat de Catalunya.
Abstract (Originalsprache)
Stochastic processes have found numerous applications in science, as they are broadly used to model a variety of natural phenomena. Due to their intrinsic randomness and uncertainty, they are, however, difficult to characterize. Here, we introduce an unsupervised machine learning approach to determine the minimal set of parameters required to effectively describe the dynamics of a stochastic process. Our method builds upon an extended β-variational autoencoder architecture. By means of simulated data sets corresponding to paradigmatic diffusion models, we showcase its effectiveness in extracting the minimal relevant parameters that accurately describe these dynamics. Furthermore, the method enables the generation of new trajectories that faithfully replicate the expected stochastic behavior. Overall, our approach enables the autonomous discovery of unknown parameters describing stochastic processes, hence enhancing our comprehension of complex phenomena across various fields.
Autor:innen und Institutionen
- ICFO-Institut de Ciències Fotòniques, The Barcelona Institute of Science and Technology, Av. Carl Friedrich Gauss 3, 08860 Castelldefels (Barcelona), Spain.
- Facultat de Ciències, Tecnologia i Enginyeries, Universitat de Vic-Universitat Central de Catalunya (UVic-UCC), C. de la Laura, 13, 08500 Vic, Spain.
- Bioinformatics and Bioimaging, Institut de Recerca i Innovació en Ciències de la Vida i de la Salut a la Catalunya Central (IRIS-CC), 08500 Vic, Barcelona, Spain.
- ICREA, Pg. Lluís Companys 23, 08010 Barcelona, Spain.
- Institute for Theoretical Physics, University of Innsbruck, Technikerstr. 21a, A-6020 Innsbruck, Austria.
Förderung
- European Commission
- Ministerio de Ciencia e Innovación
- Generalitat de Catalunya
- H2020 European Research Council
Zitieren
APA
Fernández-Fernández, G., Manzo, C., Lewenstein, M., Dauphin, A., & Muñoz-Gil, G. (2024). Learning minimal representations of stochastic processes with variational autoencoders. Physical Review E, 110(1). https://doi.org/10.1103/physreve.110.l012102
Vancouver
Fernández-Fernández G, Manzo C, Lewenstein M, Dauphin A, Muñoz-Gil G. Learning minimal representations of stochastic processes with variational autoencoders. Physical Review E. 2024;110(1). doi:10.1103/physreve.110.l012102
BibTeX
@article{FernndezFernndez2024,
author = {Fernández-Fernández, Gabriel and Manzo, Carlo and Lewenstein, Maciej and Dauphin, Alexandre and Muñoz-Gil, Gorka},
title = {Learning minimal representations of stochastic processes with variational autoencoders},
journal = {Physical Review E},
year = {2024},
volume = {110},
number = {1},
doi = {10.1103/physreve.110.l012102}
}
EUVIMED