Results 21 to 30 of about 114,837 (257)
Parametric Bayesian Estimation of Differential Entropy and Relative Entropy
Given iid samples drawn from a distribution with known parametric form, we propose the minimization of expected Bregman divergence to form Bayesian estimates of differential entropy and relative entropy, and derive such estimators for the uniform ...
Maya Gupta, Santosh Srivastava
doaj +1 more source
Relative model of the logical entropy of sub-$\sigma_\Theta$-algebras [PDF]
In the context of observers, any mathematical model according to the viewpoint of an observer $ \Theta $ is called a relative model. The purpose of the present paper is to study the relative model of logical entropy. Given an observer $ \Theta $,
Uosef Mohammadi
doaj +1 more source
Relative entropy equals bulk relative entropy
23 pages, 3 ...
Jafferis, Daniel +3 more
openaire +3 more sources
Relative cluster entropy for power-law correlated sequences
We propose an information-theoretical measure, the \textit{relative cluster entropy} $\mathcal{D_{C}}[P \| Q] $, to discriminate among cluster partitions characterised by probability distribution functions $P$ and $Q$.
Anna Carbone, Linda Ponta
doaj +1 more source
By using Araki's relative entropy, Lieb's convexity and the theory of singular integrals, we compute the mutual information associated with free fermions, and we deduce many results about entropies for chiral CFT's which are embedded into free fermions, and their extensions. Such relative entropies in CFT are here computed explicitly for the first time
Longo, Roberto, Xu, Feng
openaire +4 more sources
Dissipation, interaction, and relative entropy [PDF]
Many thermodynamic relations involve inequalities, with equality if a process does not involve dissipation. In this article we provide equalities in which the dissipative contribution is shown to involve the relative entropy (a.k.a. Kullback-Leibler divergence).
Gaveau, B. +3 more
openaire +4 more sources
A Bayesian characterization of relative entropy
We give a new characterization of relative entropy, also known as the Kullback-Leibler divergence. We use a number of interesting categories related to probability theory. In particular, we consider a category FinStat where an object is a finite set equipped with a probability distribution, while a morphism is a measure-preserving function $f: X \to Y$
Baez, John C, Fritz, Tobias
openaire +4 more sources
All Inequalities for the Relative Entropy [PDF]
15 pages, 3 embedded eps ...
Ben Ibinson +2 more
openaire +4 more sources
Entropy and Relative Entropy From Information-Theoretic Principles [PDF]
We introduce an axiomatic approach to entropies and relative entropies that relies only on minimal information-theoretic axioms, namely monotonicity under mixing and data-processing as well as additivity for product distributions. We find that these axioms induce sufficient structure to establish continuity in the interior of the probability simplex ...
Gilad Gour, Marco Tomamichel
openaire +2 more sources
The improved relative entropy for face recognition
The relative entropy is least sensitive to noise. In this paper, we propose the improved relative entropy for face recognition (IRE). The IRE method of recognition rate is far higher than the LDA, LPP method, by experimental results on CMU PIE face ...
Zhang Qi Rong, Zhang Ji Yan, Wang Yan
doaj +1 more source

