We introduce an approach which allows detecting causal relationships between variables for which the time evolution is available. Causality is assessed by a variational scheme based on the Information Imbalance of distance ranks, a statistical test capable of inferring the relative information content of different distance measures. We test whether the predictability of a putative driven system Y can be improved by incorporating information from a potential driver system X, without making assumptions on the underlying dynamics and without the need to compute probability densities of the dynamic variables. This framework makes causality detection possible even for high-dimensional systems where only few of the variables are known or measured. Benchmark tests on coupled chaotic dynamical systems demonstrate that our approach outperforms other model-free causality detection methods, successfully handling both unidirectional and bidirectional couplings. We also show that the method can be used to robustly detect causality in human electroencephalography data.
Robust inference of causality in high-dimensional dynamical processes from the Information Imbalance of distance ranks / Del Tatto, V.; Fortunato, G.; Bueti, D.; Laio, A.. - In: PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA. - ISSN 1091-6490. - 121:19(2024), pp. 1-10. [10.1073/pnas.2317256121]
Robust inference of causality in high-dimensional dynamical processes from the Information Imbalance of distance ranks
Del Tatto V.Conceptualization
;Fortunato G.Membro del Collaboration group
;Bueti D.Membro del Collaboration group
;Laio A.
Conceptualization
2024-01-01
Abstract
We introduce an approach which allows detecting causal relationships between variables for which the time evolution is available. Causality is assessed by a variational scheme based on the Information Imbalance of distance ranks, a statistical test capable of inferring the relative information content of different distance measures. We test whether the predictability of a putative driven system Y can be improved by incorporating information from a potential driver system X, without making assumptions on the underlying dynamics and without the need to compute probability densities of the dynamic variables. This framework makes causality detection possible even for high-dimensional systems where only few of the variables are known or measured. Benchmark tests on coupled chaotic dynamical systems demonstrate that our approach outperforms other model-free causality detection methods, successfully handling both unidirectional and bidirectional couplings. We also show that the method can be used to robustly detect causality in human electroencephalography data.File | Dimensione | Formato | |
---|---|---|---|
2305.10817.pdf
non disponibili
Descrizione: preprint
Tipologia:
Documento in Pre-print
Licenza:
Non specificato
Dimensione
3.15 MB
Formato
Adobe PDF
|
3.15 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
del-tatto-et-al-2024-robust-inference.pdf
accesso aperto
Descrizione: pdf editoriale
Tipologia:
Versione Editoriale (PDF)
Licenza:
Creative commons
Dimensione
23.05 MB
Formato
Adobe PDF
|
23.05 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.