Gaussian Mean Testing Made Simple

DOI10.1137/1.9781611977585.CH31MaRDI QIDQ6415002zbMATH OpenOpenAlexFDO

Authors Ilias Diakonikolas, Daniel M. Kane, Ankit Pensia

Publication date 24 October 2022

Full work available at URL https://doi.org/10.1137/1.9781611977585.ch31

Abstract: We study the following fundamental hypothesis testing problem, which we term Gaussian mean testing. Given i.i.d. samples from a distribution

p

on

m a t h b b R^{d}

, the task is to distinguish, with high probability, between the following cases: (i)

p

is the standard Gaussian distribution,

m a t h c a l N (0, I_{d})

, and (ii)

p

is a Gaussian

m a t h c a l N (m u, S i g m a)

for some unknown covariance

S i g m a

and mean

m u i n m a t h b b R^{d}

satisfying

| m u |_{2} g e q e p s i l o n

. Recent work gave an algorithm for this testing problem with the optimal sample complexity of

T h e t a (s q r t d / e p s i l o n^{2})

. Both the previous algorithm and its analysis are quite complicated. Here we give an extremely simple algorithm for Gaussian mean testing with a one-page analysis. Our algorithm is sample optimal and runs in sample linear time.

Cited in

(1)

Testing convex truncation

This page was built for publication: Gaussian Mean Testing Made Simple

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6415002)