Non asymptotic minimax rates of testing in signal detection with heterogeneous variances

preprint2010arXivOpen access

Abstract

The aim of this paper is to establish non-asymptotic minimax rates of testing for goodness-of-fit hypotheses in a heteroscedastic setting. More precisely, we deal with sequences (Yj)j∈J(Y_j)_{j\in J} of independent Gaussian random variables, having mean (θj)j∈J(θ_j)_{j\in J} and variance (σj)j∈J(σ_j)_{j\in J}. The set JJ will be either finite or countable. In particular, such a model covers the inverse problem setting where few results in test theory have been obtained. The rates of testing are obtained with respect to l2l_2 and l∞l_{\infty} norms, without assumption on (σj)j∈J(σ_j)_{j\in J} and on several functions spaces. Our point of view is completely non-asymptotic.

Explore this paper’s authors, topics and related work.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Reviews 0

Write a reviewWrite

No reviews yet.

Discussion 0

Add a commentWrite

No comments yet.