Showing cs.ITShow all
2 papers · 1 filter
cs.IT2024
An Informational Parsimony Perspective on Probabilistic Symmetries
Hippolyte Charvin, Nicola Catenacci Volpi, Daniel Polani
Extraction of structure, in particular of group symmetries, is increasingly crucial to understanding and building intelligent models. In particular, some information-theoretic mode…
cs.IT2023
Towards Information Theory-Based Discovery of Equivariances
Hippolyte Charvin, Nicola Catenacci Volpi, Daniel Polani
The presence of symmetries imposes a stringent set of constraints on a system. This constrained structure allows intelligent agents interacting with such a system to drastically im…