Journal ArticleDOI
A simple proof of the blowing-up lemma (Corresp.)
Reads0
Chats0
TLDR
Here an information-theoretic proof of the blowing-up lemma, generalizing it to continuous alphabets, is given.Abstract:
The blowing-up lemma says that if the probability with respect to a product measure of a set A\subseteq {\cal X}^{n} ({\cal X} finite, n large) is not exponentially small, then its l_{n} -neighborhood has probability almost one for some l_{n} = O(n) . Here an information-theoretic proof of the blowing-up lemma, generalizing it to continuous alphabets, is given.read more
Citations
More filters
Book
Concentration Inequalities and Model Selection
TL;DR: In this article, Gaussian Processes and Gaussian Model Selection are used to estimate density estimation via model selection via statistical learning.Exponential and Information Inequalities, Gaussian processes and model selection.
Journal ArticleDOI
Exponential Integrability and Transportation Cost Related to Logarithmic Sobolev Inequalities
Sergey G. Bobkov,Friedrich Götze +1 more
TL;DR: In this article, the authors study some problems on exponential integrability, concentration of measure, and transportation cost related to logarithmic Sobolev inequalities, and give a characterization of probability measures that satisfy these inequalities.
Book ChapterDOI
Introduction to Statistical Learning Theory
TL;DR: This tutorial introduces the techniques that are used to obtain results in the form of so-called error bounds in statistical learning theory.
Journal ArticleDOI
Theory of classification : a survey of some recent advances
TL;DR: The last few years have witnessed important new developments in the theory and practice of pattern classification, see as discussed by the authors for a survey of the main new ideas that have lead to these important recent developments.
Journal ArticleDOI
Transportation cost for Gaussian and other product measures
TL;DR: In this paper, it was shown that the transportation cost of a unit of mass from a toy to a person, when the cost of transporting a unit is measured by ∥x−y∥2, is at most $€ 1.
References
More filters
Journal ArticleDOI
The Existence of Probability Measures with Given Marginals
TL;DR: In this article, the existence of probability distributions with given marginals is studied under typically weaker assumptions, than those which are required by the use of Theorem 1, and necessary and sufficient conditions for a sequence of probability measures to be the sequence of distributions of a martingale, an upper semi-martingale or of partial sums of independent random variables.
Journal ArticleDOI
Sanov Property, Generalized $I$-Projection and a Conditional Limit Theorem
TL;DR: In this paper, it was shown that the limiting conditional distribution of (either) $X_i$ is characterized as a member of the exponential family determined by the unconditional distribution $P_X, while (X_1, \cdots, X_n) are conditionally asymptotically quasi-independent.
Journal ArticleDOI
Bounds on Conditional Probabilities with Applications in Multi-User Communication
Journal ArticleDOI
If a two-point extension of a Bernoulli shift has an ergodic square, then it is Bernoulli
TL;DR: In this paper, a notion of "nesting" for very weakly Bernoulli distributions is developed and used to prove that any two-point extension of a Bernoullis shift, if it has ergodic square, must itself be Bernoulla.
Related Papers (5)
Transportation cost for Gaussian and other product measures
Exponential Integrability and Transportation Cost Related to Logarithmic Sobolev Inequalities
Sergey G. Bobkov,Friedrich Götze +1 more