Differential Entropy on Statistical Spaces
Jacques Calmet, Xavier Calmet

TL;DR
This paper introduces a new way to define differential entropy on fuzzy statistical spaces where points are localized within volumes, impacting integrability and quantum state analysis.
Contribution
It presents a novel formalism for differential entropy on statistical spaces with fuzziness, extending traditional concepts to non-Riemann integrable contexts.
Findings
Differential entropy can be defined on fuzzy statistical spaces.
The formalism accounts for non-Riemann integrability of relevant integrals.
Application to quantum states is discussed.
Abstract
We show that the previously introduced concept of distance on statistical spaces leads to a straightforward definition of differential entropy on these statistical spaces. These spaces are characterized by the fact that their points can only be localized within a certain volume and exhibit thus a feature of fuzziness. This implies that Riemann integrability of relevant integrals is no longer secured. Some discussion on the specialization of this formalism to quantum states concludes the paper.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsStatistical Mechanics and Entropy · advanced mathematical theories · Quantum Mechanics and Applications
