A variant of the well-known Chebyshev inequality for scalar random variables
can be formulated in the case where the mean and variance are estimated from
samples. In this paper we present a generalization of this result to multiple
dimensions where the only requirement is that the samples are independent and
identically distributed. Furthermore, we show that as the number of samples
tends to infinity our inequality converges to the theoretical multi-dimensional
Chebyshev bound.
%0 Generic
%1 stellato2015multivariate
%A Stellato, Bartolomeo
%A Van Parys, Bart
%A Goulart, Paul J.
%D 2015
%K proba
%T Multivariate Chebyshev Inequality with Estimated Mean and Variance
%U http://arxiv.org/abs/1509.08398
%X A variant of the well-known Chebyshev inequality for scalar random variables
can be formulated in the case where the mean and variance are estimated from
samples. In this paper we present a generalization of this result to multiple
dimensions where the only requirement is that the samples are independent and
identically distributed. Furthermore, we show that as the number of samples
tends to infinity our inequality converges to the theoretical multi-dimensional
Chebyshev bound.
@misc{stellato2015multivariate,
abstract = {A variant of the well-known Chebyshev inequality for scalar random variables
can be formulated in the case where the mean and variance are estimated from
samples. In this paper we present a generalization of this result to multiple
dimensions where the only requirement is that the samples are independent and
identically distributed. Furthermore, we show that as the number of samples
tends to infinity our inequality converges to the theoretical multi-dimensional
Chebyshev bound.},
added-at = {2016-03-31T06:30:57.000+0200},
author = {Stellato, Bartolomeo and Van Parys, Bart and Goulart, Paul J.},
biburl = {https://www.bibsonomy.org/bibtex/21a68729483ea37a5a3bfbaeb336ddb97/pixor},
description = {1509.08398v2.pdf},
interhash = {2e1e5ae778a9d7b7a82e2a843e092acd},
intrahash = {1a68729483ea37a5a3bfbaeb336ddb97},
keywords = {proba},
note = {cite arxiv:1509.08398v2.pdf},
timestamp = {2016-03-31T06:30:57.000+0200},
title = {Multivariate Chebyshev Inequality with Estimated Mean and Variance},
url = {http://arxiv.org/abs/1509.08398},
year = 2015
}