Information theory and statistics: a tutorial
Communications and Information Theory
Outage behavior of discrete memoryless channels under channel estimation errors
IEEE Transactions on Information Theory
Finiteness of redundancy, regret, Shtarkov sums, and Jeffreys integrals in exponential families
ISIT'09 Proceedings of the 2009 IEEE international conference on Symposium on Information Theory - Volume 1
Divergence from factorizable distributions and matroid representations by partitions
IEEE Transactions on Information Theory
Localization in underwater dispersive channels using the time-frequency-phase continuity of signals
IEEE Transactions on Signal Processing
Belief propagation, Dykstra's algorithm, and iterated information projections
IEEE Transactions on Information Theory
Linear universal decoding for compound channels
IEEE Transactions on Information Theory
Learning High-Dimensional Markov Forest Distributions: Analysis of Error Rates
The Journal of Machine Learning Research
Hi-index | 755.08 |
The goal of this paper is to complete results available about I-projections, reverse I-projections, and their generalized versions, with focus on linear and exponential families. Pythagorean-like identities and inequalities are revisited and generalized, and generalized maximum-likelihood (ML) estimates for exponential families are introduced. The main tool is a new concept of extension of exponential families, based on our earlier results on convex cores of measures.