English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Journal Article

Renormalized Mutual Information for Artificial Scientific Discovery

MPS-Authors

Sarra,  Leopoldo
Marquardt Division, Max Planck Institute for the Science of Light, Max Planck Society;

/persons/resource/persons200999

Aiello,  Andrea
Marquardt Division, Max Planck Institute for the Science of Light, Max Planck Society;

/persons/resource/persons201125

Marquardt,  Florian
Marquardt Division, Max Planck Institute for the Science of Light, Max Planck Society;
Department of Physics, Friedrich-Alexander Universität Erlangen-Nürnberg;

External Resource
No external resources are shared
Fulltext (public)

PhysRevLett.126.200601.pdf
(Any fulltext), 795KB

Supplementary Material (public)

2020_Sarra.png
(Supplementary material), 74KB

Citation

Sarra, L., Aiello, A., & Marquardt, F. (2021). Renormalized Mutual Information for Artificial Scientific Discovery. Physical Review Letters, 126: 200601. doi:10.1103/PhysRevLett.126.200601.


Cite as: http://hdl.handle.net/21.11116/0000-0006-89F5-B
Abstract
We derive a well-defined renormalized version of mutual information that allows 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.