Rescaling Entropy and Divergence Rates

Loïck Lhote 1 Valérie Girardin 2
1 Equipe AMACC - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : Based on rescaling by some suitable sequence instead of the number of time units, the usual notion of divergence rate is here extended to define and determine meaningful generalized divergence rates. Rescaling entropy rates appears as a special case. Suitable rescaling is naturally induced by the asymptotic behavior of the marginal divergences. Closed form formulas are obtained as soon as the marginal divergences behave like powers of some analytical functions. A wide class of countable Markov chains is proven to satisfy this property. Most divergence and entropy functionals defined in the literature are concerned, e.g., the classical Shannon, Kullback-Leibler, R´enyi, Tsallis. For illustration purposes, Ferreri or Basu-Harris-Hjort-Jones – among others – are also considered.
Type de document :
Article dans une revue
IEEE Transactions on Information Theory, Institute of Electrical and Electronics Engineers, 2015, 61 (11), pp.5868-5882. 〈10.1109/TIT.2015.2476486〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01196817
Contributeur : Référent Amacc Référent de L'Équipe Amacc - Laboratoire Greyc - Umr6072 <>
Soumis le : jeudi 10 septembre 2015 - 14:41:22
Dernière modification le : mardi 26 septembre 2017 - 01:12:12

Identifiants

Citation

Loïck Lhote, Valérie Girardin. Rescaling Entropy and Divergence Rates. IEEE Transactions on Information Theory, Institute of Electrical and Electronics Engineers, 2015, 61 (11), pp.5868-5882. 〈10.1109/TIT.2015.2476486〉. 〈hal-01196817〉

Partager

Métriques

Consultations de la notice

90