Entropy of the Mixture of Sources and Entropy Dimension
Marek Smieja, Jacek Tabor
TL;DR
This paper explores the entropy and entropy dimension of mixtures of sources, providing estimations for convex combinations of measures using a novel entropy definition based on measures rather than partitions.
Contribution
It introduces an alternative entropy definition and offers estimations for the entropy and entropy dimension of source mixtures.
Findings
Provided bounds for entropy of convex measure combinations
Developed a new entropy definition based on measures
Extended understanding of entropy dimension in source mixtures
Abstract
We investigate the problem of the entropy of the mixture of sources. There is given an estimation of the entropy and entropy dimension of convex combination of measures. The proof is based on our alternative definition of the entropy based on measures instead of partitions.
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 · Mathematical Dynamics and Fractals · Control Systems and Identification