Accueil > Activités > Séminaires > Séminaire doctorant > Archives des séminaires 2023-2024

On the Ziv-Merhav theorem beyond Markovianity

par Peru Florian - publié le

Lundi 15 Janvier 2024 à 14h00
Nicholas Barnfield
(McGill University, Montreal)

On the Ziv-Merhav theorem beyond Markovianity

In 1993, Ziv and Merhav proposed a “new notion of empirical informational divergence”, or relative-entropy estimator which has met great practical application, yet has seen no significant development in the mathematical literature until recently. In this talk, I will compare their algorithm with more conventional universal entropic estimators and discuss a recent generalization of the Ziv-Merhav Theorem. This extension encompasses a broader class of decoupled measures including the the class of multi-level Markov measures covered by the original result as well as suitably regular g-measures amongst other examples. Joint work with R. Grondin, G. Pozzoli, and R. Raquépas.