Minimal Joint Entropy and Order-Preserving Couplings
Ya-Jing Ma, Feng Wang, Xian-Yuan Wu, Kai-Yuan Cai

TL;DR
This paper investigates the extremal values of Shannon entropy for joint distributions with fixed marginals, revealing that minimum entropy couplings are order-preserving and maximum entropy couplings are independent, providing insights into system disorder.
Contribution
It proves that the minimal entropy coupling must be order-preserving, a novel characterization in the study of joint distributions with fixed marginals.
Findings
Minimum-entropy coupling is order-preserving.
Maximum-entropy coupling is the independent distribution.
Entropy measures system disorder in joint distributions.
Abstract
This paper focuses on the extreme-value problem for Shannon entropy of the joint distribution with given marginals. It is proved that the minimum-entropy coupling must be of order-preserving, while the maximum-entropy coupling coincides with the independent one. Note that in this sense, we interpret entropy as a measure of system disorder.
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 · stochastic dynamics and bifurcation
