Variations and extensions of the Gaussian concentration inequality, Part I

  title={Variations and extensions of the Gaussian concentration inequality, Part I},
  author={Daniel J. Fresen},
  journal={Quaestiones Mathematicae},
We use and modify the Gaussian concentration inequality to prove a variety of concentration inequalities for a wide class of functions and measures on $\mathbb{R}^{n}$, typically involving independence, various types of decay (including exponential, Weibull $0 2$) that go deeper into the tails than does the weighted Berry-Esseen inequality. We use these methods to study random sections of convex bodies, proving a variation of Milman's general Dvoretzky theorem for non-Gaussian random matricies… 
5 Citations

Moment free deviation inequalities for linear combinations of independent random variables with power-type tails

We present order of magnitude estimates for the quantiles of non-negative linear combinations of non-negative random variables, as well as deviation inequalities for general linear combinations of

Convex subsets of non-convex Lorentz balls

Borders on the distribution of certain functions of a Gaussian random vector are derived by approximating their sub-level sets by convex subsets by Gaussian measure.

Optimal tail comparison under convex majorization

Following results of Kemperman and Pinelis, we show that if X and Y are real valued random variables such that E | Y | < ∞ and for all non-decreasing convex ϕ : R → [0 , ∞ ), E ϕ ( X ) ≤ E ϕ ( Y ),

A Continuous-Time Mirror Descent Approach to Sparse Phase Retrieval

This work applies mirror descent to the unconstrained empirical risk minimization problem (batch setting), using the square loss and square measurements, and provides a convergence analysis of the algorithm in this non-convex setting and proves that, with the hypentropy mirror map, mirror descent recovers any $k$-sparse vector.

Random Euclidean embeddings in finite-dimensional Lorentz spaces

Quantitative bounds for random embeddings of Rk into Lorentz sequence spaces are given, with improved dependence on ε.



A note on the Hanson-Wright inequality for random vectors with dependencies

We prove that quadratic forms in isotropic random vectors $X$ in $\mathbb{R}^n$, possessing the convex concentration property with constant $K$, satisfy the Hanson-Wright inequality with constant

Poincaré inequalities and dimension free concentration of measure

In this paper, we consider Poincare inequalities for non euclidean metrics on $\mathbb{R}^d$. These inequalities enable us to derive precise dimension free concentration inequalities for product

Concentration Inequalities - A Nonasymptotic Theory of Independence

Deep connections with isoperimetric problems are revealed whilst special attention is paid to applications to the supremum of empirical processes.

Functional Inequalities for Heavy Tailed Distributions and Application to Isoperimetry

This paper is devoted to the study of probability measures with heavy tails. Using the Lyapunov function approach we prove that such measures satisfy different kind of functional inequalities such as

A multivariate Gnedenko law of large numbers

We show that the convex hull of a large i.i.d. sample from an absolutely continuous log-concave distribution approximates a predetermined convex body in the logarithmic Hausdorff distance and in the

Non asymptotic variance bounds and deviation inequalities by optimal transport

  • K. Tanguy
  • Mathematics
    Electronic Journal of Probability
  • 2019
The purpose of this note is to show how simple optimal transport arguments, on the real line, can be used in Superconcentration theory. As such, we derive non- asymptotic sharp variance bounds for

A large deviation theorem for weighted sums

Asymptotic representations are derived for large deviation probabilities of weighted sums of independent, identically distributed random variables. The main theorem generalizes a 1952 theorem of

Moment inequalities for sums of certain independent symmetric random variables

This paper gives upper and lower bounds for moments of sums of independent random variables (Xk) which satisfy the condition that P (|X|k ≥ t) = exp(−Nk(t)), where Nk are concave functions. As a

Concentration inequalities for order statistics

This note describes non-asymptotic variance and tail bounds for order statistics of samples of independent identically distributed random variables. When the sampling distribution belongs to a

Optimal Tail Comparison Based on Comparison of Moments

Many of extremal problems of probability and statistics may be put in the following general form. Suppose that one has a moment comparison inequality where ξ and η are random elements of a measurable