SΩI: Score-based O-INFORMATION Estimation - EURECOM Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

SΩI: Score-based O-INFORMATION Estimation

Résumé

The analysis of scientific data and complex mul-tivariate systems requires information quantities that capture relationships among multiple random variables. Recently, new information-theoretic measures have been developed to overcome the shortcomings of classical ones, such as mutual information, that are restricted to considering pair-wise interactions. Among them, the concept of information synergy and redundancy is crucial for understanding the high-order dependencies between variables. One of the most prominent and versatile measures based on this concept is O-INFORMATION, which provides a clear and scalable way to quantify the synergy-redundancy balance in multivariate systems. However, its practical application is limited to simplified cases. In this work, we introduce SΩI, which allows to compute O-INFORMATION without restrictive assumptions about the system while leveraging a unique model. Our experiments validate our approach on synthetic data, and demonstrate the effectiveness of SΩI in the context of a real-world use case.
Fichier principal
Vignette du fichier
5503_s_omega_i_score_based_o_inform (1).pdf (8.06 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04653132 , version 1 (18-07-2024)

Identifiants

Citer

Mustapha Bounoua, Giulio Franzese, Pietro Michiardi. SΩI: Score-based O-INFORMATION Estimation. ICML 2024, 41st International Conference on Machine Learning, IEEE, Jul 2024, Vienna, Austria. ⟨hal-04653132⟩

Collections

EURECOM
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More