Number of the records: 1
Maximization of the information divergence from an exponential family and criticality
- 1.
SYSNO ASEP 0363274 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Maximization of the information divergence from an exponential family and criticality Author(s) Matúš, František (UTIA-B) RID
Rauh, J. (DE)Number of authors 2 Source Title Proceedings ISIT 2011. - Piscataway : IEEE, 2011 - ISBN 978-1-4577-0595-3 Pages s. 903-907 Number of pages 5 s. Action IEEE Internation Symposioum on Information Theory Event date 31.07.2011-05.08.2011 VEvent location St. Petersburg Country RU - Russian Federation Event type WRD Language eng - English Country RU - Russian Federation Keywords exponential family ; information divergence ; critical sets Subject RIV BD - Theory of Information R&D Projects GAP202/10/0618 GA ČR - Czech Science Foundation (CSF) CEZ AV0Z10750506 - UTIA-B (2005-2011) UT WOS 000297465101017 DOI 10.1109/ISIT.2011.6034269 Annotation The problem to maximize the information divergence from an exponential family is compared to the maximization of an entropy-like quantity over the boundary of a polytope. First-order conditions on directional derivatives define critical sets for the two problems. The bijection between the sets of global maximizers in the two problems found earlier is extended here to bijections between the sets of local maximizers and the critical sets. This is based on new inequalities relating the maximized quantities and a reformulation of the first order criticality conditions for the second problem. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Year of Publishing 2012
Number of the records: 1