Cargando…

Inference in conditioned dynamics through causality restoration

Estimating observables from conditioned dynamics is typically computationally hard. While obtaining independent samples efficiently from unconditioned dynamics is usually feasible, most of them do not satisfy the imposed conditions and must be discarded. On the other hand, conditioning breaks the ca...

Descripción completa

Detalles Bibliográficos
Autores principales: Braunstein, Alfredo, Catania, Giovanni, Dall’Asta, Luca, Mariani, Matteo, Muntoni, Anna Paola
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10163042/
https://www.ncbi.nlm.nih.gov/pubmed/37147382
http://dx.doi.org/10.1038/s41598-023-33770-3
_version_ 1785037811107233792
author Braunstein, Alfredo
Catania, Giovanni
Dall’Asta, Luca
Mariani, Matteo
Muntoni, Anna Paola
author_facet Braunstein, Alfredo
Catania, Giovanni
Dall’Asta, Luca
Mariani, Matteo
Muntoni, Anna Paola
author_sort Braunstein, Alfredo
collection PubMed
description Estimating observables from conditioned dynamics is typically computationally hard. While obtaining independent samples efficiently from unconditioned dynamics is usually feasible, most of them do not satisfy the imposed conditions and must be discarded. On the other hand, conditioning breaks the causal properties of the dynamics, which ultimately renders the sampling of the conditioned dynamics non-trivial and inefficient. In this work, a Causal Variational Approach is proposed, as an approximate method to generate independent samples from a conditioned distribution. The procedure relies on learning the parameters of a generalized dynamical model that optimally describes the conditioned distribution in a variational sense. The outcome is an effective and unconditioned dynamical model from which one can trivially obtain independent samples, effectively restoring the causality of the conditioned dynamics. The consequences are twofold: the method allows one to efficiently compute observables from the conditioned dynamics by averaging over independent samples; moreover, it provides an effective unconditioned distribution that is easy to interpret. This approximation can be applied virtually to any dynamics. The application of the method to epidemic inference is discussed in detail. The results of direct comparison with state-of-the-art inference methods, including the soft-margin approach and mean-field methods, are promising.
format Online
Article
Text
id pubmed-10163042
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-101630422023-05-07 Inference in conditioned dynamics through causality restoration Braunstein, Alfredo Catania, Giovanni Dall’Asta, Luca Mariani, Matteo Muntoni, Anna Paola Sci Rep Article Estimating observables from conditioned dynamics is typically computationally hard. While obtaining independent samples efficiently from unconditioned dynamics is usually feasible, most of them do not satisfy the imposed conditions and must be discarded. On the other hand, conditioning breaks the causal properties of the dynamics, which ultimately renders the sampling of the conditioned dynamics non-trivial and inefficient. In this work, a Causal Variational Approach is proposed, as an approximate method to generate independent samples from a conditioned distribution. The procedure relies on learning the parameters of a generalized dynamical model that optimally describes the conditioned distribution in a variational sense. The outcome is an effective and unconditioned dynamical model from which one can trivially obtain independent samples, effectively restoring the causality of the conditioned dynamics. The consequences are twofold: the method allows one to efficiently compute observables from the conditioned dynamics by averaging over independent samples; moreover, it provides an effective unconditioned distribution that is easy to interpret. This approximation can be applied virtually to any dynamics. The application of the method to epidemic inference is discussed in detail. The results of direct comparison with state-of-the-art inference methods, including the soft-margin approach and mean-field methods, are promising. Nature Publishing Group UK 2023-05-05 /pmc/articles/PMC10163042/ /pubmed/37147382 http://dx.doi.org/10.1038/s41598-023-33770-3 Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Braunstein, Alfredo
Catania, Giovanni
Dall’Asta, Luca
Mariani, Matteo
Muntoni, Anna Paola
Inference in conditioned dynamics through causality restoration
title Inference in conditioned dynamics through causality restoration
title_full Inference in conditioned dynamics through causality restoration
title_fullStr Inference in conditioned dynamics through causality restoration
title_full_unstemmed Inference in conditioned dynamics through causality restoration
title_short Inference in conditioned dynamics through causality restoration
title_sort inference in conditioned dynamics through causality restoration
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10163042/
https://www.ncbi.nlm.nih.gov/pubmed/37147382
http://dx.doi.org/10.1038/s41598-023-33770-3
work_keys_str_mv AT braunsteinalfredo inferenceinconditioneddynamicsthroughcausalityrestoration
AT cataniagiovanni inferenceinconditioneddynamicsthroughcausalityrestoration
AT dallastaluca inferenceinconditioneddynamicsthroughcausalityrestoration
AT marianimatteo inferenceinconditioneddynamicsthroughcausalityrestoration
AT muntoniannapaola inferenceinconditioneddynamicsthroughcausalityrestoration