On asymptotic properties of information-theoretic divergences



Downloads per month over past year

Pardo Llorente, María del Carmen and Vajda, Igor (2003) On asymptotic properties of information-theoretic divergences. IEEE transactions on information theory, 49 (7). pp. 1860-1867. ISSN 0018-9448

[thumbnail of PardoCarmen07.pdf] PDF
Restringido a Repository staff only


Official URL: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1207389


Abstract—Mutual asymptotic equivalence is established within three classes of information-theoretic divergences of discrete probability distributions, namely, -divergences of Csiszár, -divergences of Bregman, and -divergences of Burbea–Rao. These equivalences are used to find asymptotic distributions of the corresponding divergence statistics for
testing the goodness of fit when the hypothetic distribution is uniform. All results are based on standard expansion techniques and on a new relation between the Bregman and Burbea–Rao divergences formulated in Lemma 2.

Item Type:Article
Uncontrolled Keywords:Terms—Asymptotic distributions; Asymptotic equivalence; Bregman divergences; Burbea–Rao divergences; Divergences of Csiszár; Divergence statistics.
Subjects:Social sciences > Information science > Information theory
ID Code:17586
Deposited On:10 Jan 2013 09:52
Last Modified:20 Feb 2019 11:13

Origin of downloads

Repository Staff Only: item control page