Concentration Inequalities
نویسنده
چکیده
1.1. Azuma-Hoeffding Inequality. Concentration inequalities are inequalities that bound probabilities of deviations by a random variable from its mean or median. Our interest will be in concentration inequalities in which the deviation probabilities decay exponentially or superexponentially in the distance from the mean. One of the most basic such inequality is the Azuma-Hoeffding inequality for sums of bounded random variables.
منابع مشابه
Concentration inequalities and martingale inequalities — a survey
We examine a number of generalized and extended versions of concentration inequalities and martingale inequalities. These inequalities are effective for analyzing processes with quite general conditions as illustrated in an example for an infinite Polya process and webgraphs.
متن کاملEntropy-Based Concentration Inequalities for Dependent Variables
We provide new concentration inequalities for functions of dependent variables. The work extends that of Janson (2004), which proposes concentration inequalities using a combination of the Laplace transform and the idea of fractional graph coloring, as well as many works that derive concentration inequalities using the entropy method (see, e.g., (Boucheron et al., 2003)). We give inequalities f...
متن کاملConcentration of Measure Inequalities in Information Theory, Communications, and Coding Concentration of Measure Inequalities in Information Theory, Communications, and Coding
During the last two decades, concentration inequalities have been the subject of exciting developments in various areas, including convex geometry, functional analysis, statistical physics, high-dimensional statistics, pure and applied probability theory (e.g., concentration of measure phenomena in random graphs, random matrices, and percolation), information theory, theoretical computer scienc...
متن کاملConcentration inequalities for random fields via coupling
We present a new and simple approach to concentration inequalities for functions around their expectation with respect to non-product measures, i.e., for dependent random variables. Our method is based on coupling ideas and does not use information inequalities. When one has a uniform control on the coupling, this leads to exponential concentration inequalities. When such a uniform control is n...
متن کاملDecomposition of s ― Concentration Curves
For any given order of stochastic dominance, standard concentration curves are decomposed into contribution curves corresponding to within-group inequalities, between-group inequalities, and transvariational inequalities. We prove, for all orders, that contribution curve dominance implies systematically welfare-improving tax reforms and conversely. Accordingly, we point out some undesirable fis...
متن کامل