Sample-Optimal Identity Testing with High Probability

international colloquium on automata, languages and programming, pp. 41:1-41:14, 2018.

Cited by: 13|Bibtex|Views52|Links
EI

Abstract:

We study the problem of testing identity against a given distribution (a.k.a. goodness-of-fit) with a focus on the high confidence regime. More precisely, given samples from an unknown distribution $p$ over $n$ elements, an explicitly given distribution $q$, and parameters $0u003c epsilon, delta u003c 1$, we wish to distinguish, with prob...More

Code:

Data:

Your rating :
0

 

Tags
Comments