AI Chat AI Image Generator AI Video Text to Speech

Concentration of quadratic forms under a Bernstein moment assumption

01/25/2019

∙

by Pierre C. Bellec, et al.

∙

∙

A concentration result for quadratic form of independent subgaussian random variables is derived. If the moments of the random variables satisfy a "Bernstein condition", then the variance term of the Hanson-Wright inequality can be improved. The Bernstein condition is satisfied, for instance, by all log-concave subgaussian distributions.

page 1

page 2

page 3

page 4

research

∙ 05/17/2022

Moments, Concentration, and Entropy of Log-Concave Distributions

We utilize and extend a simple and classical mechanism, combining log-co...

0 Arnaud Marsiglietti, et al. ∙

research

∙ 11/01/2018

Hanson-Wright inequality in Banach spaces

We discuss two-sided bounds for moments and tails of quadratic forms in ...

0 Radosław Adamczak, et al. ∙

research

∙ 11/13/2019

Improved Concentration Bounds for Gaussian Quadratic Forms

For a wide class of monotonic functions f, we develop a Chernoff-style c...

0 Robert E. Gallagher, et al. ∙

research

∙ 08/20/2020

Simple Analysis of Johnson-Lindenstrauss Transform under Neuroscience Constraints

The paper re-analyzes a version of the celebrated Johnson-Lindenstrauss ...

0 Maciej Skorski, et al. ∙

research

∙ 09/13/2022

Sparse Hanson-Wright Inequality for a Bilinear Form of Sub-Gaussian Variables

In this paper, we derive a new version of Hanson-Wright inequality for a...

0 Seongoh Park, et al. ∙

research

∙ 05/24/2020

Sharp variance-entropy comparison for nonnegative gaussian quadratic forms

In this article we study quadratic forms in n independent standard norma...

0 Piotr Nayar, et al. ∙

research

∙ 07/01/2022

Prediction of random variables by excursion metric projections

We use the concept of excursions for the prediction of random variables ...

0 Vitalii Makogin, et al. ∙