• Publications
  • Influence
Minimax Estimation of Functionals of Discrete Distributions
TLDR
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 the case of discrete distributions, where the support size S is comparable with or even much larger than the number of observations n. Expand
  • 190
  • 25
  • PDF
Maximum Likelihood Estimation of Functionals of Discrete Distributions
TLDR
We consider the problem of estimating functionals of discrete distributions, and focus on a tight (up to universal multiplicative constants for each specific functional) nonasymptotic analysis of the worst case squared error risk of widely used estimators. Expand
  • 75
  • 3
  • PDF
Order-Optimal Estimation of Functionals of Discrete Distributions
  • 10
  • 3
Justification of Logarithmic Loss via the Benefit of Side Information
TLDR
We consider a natural measure of relevance: the reduction in optimal prediction risk in the presence of side information. Expand
  • 34
  • 2
  • PDF
Information Measures: The Curious Case of the Binary Alphabet
TLDR
We show that f-divergences are not the unique decomposable divergences on binary alphabets that satisfy the data processing inequality, thereby clarifying claims that have previously appeared in the literature. Expand
  • 30
  • 1
  • PDF
Relations between information and estimation in scalar Lévy channels
TLDR
We introduce the natural family of scalar Lévy channels where the distribution of the output conditioned on the input is infinitely divisible. Expand
  • 13
  • 1
  • PDF
Pointwise Relations Between Information and Estimation in Gaussian Noise
TLDR
We explore the nature of the pointwise relations between information theoretic quantities in the presence of Gaussian noise and show that they can be viewed as identities between expectations of random quantities. Expand
  • 7
  • 1
Delving into the digital divide
The author examines the question of whether the digital divide due to poverty or an effect of underlying social and economic conditions. The digital divide is a major concern to technology companies,Expand
  • 16
  • 1
Reference based genome compression
TLDR
We propose an algorithm to compress a target genome given a known reference genome, and then compresses this mapping with an entropy coder. Expand
  • 27
  • PDF