A Bernstein-type inequality for stochastic processes of quadratic forms of Gaussian variables
Statistics Theory
2009-09-22 v1 Probability
Machine Learning
Statistics Theory
Abstract
We introduce a Bernstein-type inequality which serves to uniformly control quadratic forms of gaussian variables. The latter can for example be used to derive sharp model selection criteria for linear estimation in linear regression and linear inverse problems via penalization, and we do not exclude that its scope of application can be made even broader.
Keywords
Cite
@article{arxiv.0909.3595,
title = {A Bernstein-type inequality for stochastic processes of quadratic forms of Gaussian variables},
author = {Ikhlef Bechar},
journal= {arXiv preprint arXiv:0909.3595},
year = {2009}
}