On weighted Fisher information matrix properties
Mark Kelbert, Yuri Suhov, Salimeh Yasaei Sekeh

TL;DR
This paper explores properties of weighted Fisher information matrices, extending known inequalities and identities, and offers new insights into entropy power concavity through generalized identities and bounds.
Contribution
It introduces an extended Fisher information inequality and a generalized De-Bruijn's identity, providing new theoretical insights into weighted Fisher information and entropy power.
Findings
Extended Fisher information inequality established.
New interpretation of entropy power concavity.
Bounds on weighted Fisher information discussed.
Abstract
In this paper, we review Fisher information matrices properties in weighted version and discuss inequalities/bounds on it by using reduced weight functions. In particular, an extended form of the Fisher information inequality previously established in [6] is given. Further, along with generalized De-Bruijn's identity, we provide new interpretation of the concavity for the entropy power.
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 · Sparse and Compressive Sensing Techniques · Blind Source Separation Techniques
