Renormalized Mutual Information for Artificial Scientific Discovery

Sarra L, Marquardt F, Aiello A (2021)

Publication Type: Journal article

Publication year: 2021

Journal

Physical Review Letters American Physical Society

Book Volume: 126

Article Number: 200601

Journal Issue: 20

DOI: 10.1103/PhysRevLett.126.200601

Abstract

We derive a well-defined renormalized version of mutual information that allows us to estimate the dependence between continuous random variables in the important case when one is deterministically dependent on the other. This is the situation relevant for feature extraction, where the goal is to produce a low-dimensional effective description of a high-dimensional system. Our approach enables the discovery of collective variables in physical systems, thus adding to the toolbox of artificial scientific discovery, while also aiding the analysis of information flow in artificial neural networks.

Authors with CRIS profile

Andrea Aiello

Involved external institutions

Max-Planck-Institut für die Physik des Lichts (MPL) / Max Planck Institute for the Science of Light DE Germany (DE)

How to cite

APA:

Sarra, L., Marquardt, F., & Aiello, A. (2021). Renormalized Mutual Information for Artificial Scientific Discovery. Physical Review Letters, 126(20). https://doi.org/10.1103/PhysRevLett.126.200601

MLA:

Sarra, Leopoldo, Florian Marquardt, and Andrea Aiello. "Renormalized Mutual Information for Artificial Scientific Discovery." Physical Review Letters 126.20 (2021).

BibTeX: Download