Minimax estimation of functionals of discrete distributions
We propose a general methodology for the construction and analysis of essentially minimax
estimators for a wide class of functionals of finite dimensional parameters, and elaborate on …
estimators for a wide class of functionals of finite dimensional parameters, and elaborate on …
Minimax rates of entropy estimation on large alphabets via best polynomial approximation
Consider the problem of estimating the Shannon entropy of a distribution over k elements
from n independent samples. We show that the minimax mean-square error is within the …
from n independent samples. We show that the minimax mean-square error is within the …
Concentration of measure inequalities in information theory, communications, and coding
M Raginsky, I Sason - Foundations and Trends® in …, 2013 - nowpublishers.com
Concentration inequalities have been the subject of exciting developments during the last
two decades, and have been intensively studied and used as a powerful tool in various …
two decades, and have been intensively studied and used as a powerful tool in various …
Polynomial methods in statistical inference: theory and practice
This survey provides an exposition of a suite of techniques based on the theory of
polynomials, collectively referred to as polynomial methods, which have recently been …
polynomials, collectively referred to as polynomial methods, which have recently been …
Characterizing protease specificity: how many substrates do we need?
Calculation of cleavage entropies allows to quantify, map and compare protease substrate
specificity by an information entropy based approach. The metric intrinsically depends on …
specificity by an information entropy based approach. The metric intrinsically depends on …
The bethe and sinkhorn approximations of the pattern maximum likelihood estimate and their connections to the valiant-valiant estimate
PO Vontobel - 2014 Information Theory and Applications …, 2014 - ieeexplore.ieee.org
For estimating a source's distribution histogram, Orlitsky and co-workers have proposed the
pattern maximum likelihood (PML) estimate, which says that one should choose the …
pattern maximum likelihood (PML) estimate, which says that one should choose the …
Classification of homogeneous data with large alphabets
BG Kelly, AB Wagner, T Tularak… - IEEE transactions on …, 2012 - ieeexplore.ieee.org
Given training sequences generated by two distinct, but unknown, distributions on a
common alphabet, we study the problem of determining whether a third sequence was …
common alphabet, we study the problem of determining whether a third sequence was …
The Bethe approximation of the pattern maximum likelihood distribution
PO Vontobel - 2012 IEEE International Symposium on …, 2012 - ieeexplore.ieee.org
Among all memoryless source distributions, the pattern maximum likelihood (PML)
distribution is the distribution which maximizes the probability that a memoryless source …
distribution is the distribution which maximizes the probability that a memoryless source …
Generalized error exponents for small sample universal hypothesis testing
The small sample universal hypothesis testing problem is investigated in this paper, in which
the number of samples n is smaller than the number of possible outcomes m. The goal of …
the number of samples n is smaller than the number of possible outcomes m. The goal of …
On refined versions of the Azuma-Hoeffding inequality with applications in information theory
I Sason - arXiv preprint arXiv:1111.1977, 2011 - arxiv.org
On Refined Versions of the Azuma-Hoeffding Inequality with Applications in Information
Theory Page 1 arXiv:1111.1977v9 [cs.IT] 13 Mar 2013 SURVEY 1 On Refined Versions of …
Theory Page 1 arXiv:1111.1977v9 [cs.IT] 13 Mar 2013 SURVEY 1 On Refined Versions of …