Concentration inequality

In probability theory, concentration inequalities provide bounds on how a random variable deviates from some value (typically, its expected value). The law of large numbers of classical probability theory states that sums of independent random variables are, under very mild conditions, close to their expectation with a large probability. Such sums are the most basic examples of random variables concentrated around their mean. Recent results show that such behavior is shared by other functions of independent random variables. Concentration inequalities can be sorted according to how much information about the random variable is needed in order to use them. Markov's inequality Let be a random variable that is non-negative (almost surely). Then, for every constant , Note the following extension to Markov's inequality: if is a strictly increasing and non-negative function, then Chebyshev's inequality Chebyshev's inequality requires the following information on a random variable : The expected value is finite. The variance is finite. Then, for every constant , or equivalently, where is the standard deviation of . Chebyshev's inequality can be seen as a special case of the generalized Markov's inequality applied to the random variable with . Vysochanskij–Petunin inequalityLet X be a random variable with unimodal distribution, mean μ and finite, non-zero variance σ2. Then, for any (For a relatively elementary proof see e.g. ). Vysochanskij–Petunin inequality For a unimodal random variable and , the one-sided Vysochanskij-Petunin inequality holds as follows: Paley–Zygmund inequality Cantelli's inequality Gauss's inequality Chernoff bound The generic Chernoff bound requires the moment generating function of , defined as It always exists, but may be infinite. From Markov's inequality, for every : and for every : There are various Chernoff bounds for different distributions and different values of the parameter . See for a compilation of more concentration inequalities.

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related publications (1)

Related concepts (4)

Related courses (6)

Related lectures (40)

A Covariance Formula For Topological Events Of Smooth Gaussian Fields

Alejandro Rivera

We derive a covariance formula for the class of 'topological events' of smooth Gaussian fields on manifolds; these are events that depend only on the topology of the level sets of the field, for examp

INST MATHEMATICAL STATISTICS2020

Hoeffding's inequality

In probability theory, Hoeffding's inequality provides an upper bound on the probability that the sum of bounded independent random variables deviates from its expected value by more than a certain amount. Hoeffding's inequality was proven by Wassily Hoeffding in 1963. Hoeffding's inequality is a special case of the Azuma–Hoeffding inequality and McDiarmid's inequality. It is similar to the Chernoff bound, but tends to be less sharp, in particular when the variance of the random variables is small.

Concentration inequality

Bernstein inequalities (probability theory)

In probability theory, Bernstein inequalities give bounds on the probability that the sum of random variables deviates from its mean. In the simplest case, let X1, ..., Xn be independent Bernoulli random variables taking values +1 and −1 with probability 1/2 (this distribution is also known as the Rademacher distribution), then for every positive , Bernstein inequalities were proven and published by Sergei Bernstein in the 1920s and 1930s. Later, these inequalities were rediscovered several times in various forms.

COM-417: Advanced probability and applications

In this course, various aspects of probability theory are considered. The first part is devoted to the main theorems in the field (law of large numbers, central limit theorem, concentration inequaliti

MATH-496: Computational linear algebra

This is an introductory course to the concentration of measure phenomenon - random functions that depend on many random variables tend to be often close to constant functions.

COM-406: Foundations of Data Science

We discuss a set of topics that are important for the understanding of modern data science but that are typically not taught in an introductory ML course. In particular we discuss fundamental ideas an

Martingales and Conditional Expectations MATH-467: Probabilistic methods in combinatorics

Explores Brun's Sieve, Martingales, and Conditional Expectations in probability theory.

High probability learning guarantees MATH-412: Statistical machine learning

Explores Talagrand's lemma, Rademacher complexity bounds, and high probability guarantees in learning.

McDiarmid's Inequality: Proof and Applications COM-417: Advanced probability and applications

Covers McDiarmid's inequality, providing concentration bounds for functions of independent random variables.