Relative information spectra with applications to statistical inference
For any pair of probability measures defined on a common space, their relative information spectra——specifically, the distribution functions of the loglikelihood ratio under either probability measure——fully encapsulate all that is relevant for distinguishing them. This paper explores the properties...
Saved in:
Main Author: | Sergio Verdú |
---|---|
Format: | Article |
Language: | English |
Published: |
AIMS Press
2024-12-01
|
Series: | AIMS Mathematics |
Subjects: | |
Online Access: | https://www.aimspress.com/article/doi/10.3934/math.20241668 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
ϵ-Confidence Approximately Correct (ϵ-CoAC) Learnability and Hyperparameter Selection in Linear Regression Modeling
by: Soosan Beheshti, et al.
Published: (2025-01-01) -
The effect of interspike interval statistics on the information gainunder the rate coding hypothesis
by: Shinsuke Koyama, et al.
Published: (2013-08-01) -
Assessing the Impact of Physical Activity on Dementia Progression Using Clustering and the MRI-Based Kullback–Leibler Divergence
by: Agnieszka Wosiak, et al.
Published: (2025-01-01) -
Some puzzles appearing in statistical inference
by: Alemam, Seyf, et al.
Published: (2024-11-01) -
On maximum-entropy and related principles in statistical equilibrium
by: C. G. Chakrabarti, et al.
Published: (1990-01-01)