On Identifying a Massive Number of Distributions
Information Theory
2018-10-16 v1 math.IT
Abstract
Finding the underlying probability distributions of a set of observed sequences under the constraint that each sequence is generated i.i.d by a distinct distribution is considered. The number of distributions, and hence the number of observed sequences, are let to grow with the observation blocklength . Asymptotically matching upper and lower bounds on the probability of error are derived.
Cite
@article{arxiv.1801.04593,
title = {On Identifying a Massive Number of Distributions},
author = {Sara Shahi and Daniela Tuninetti and Natasha Devroye},
journal= {arXiv preprint arXiv:1801.04593},
year = {2018}
}
Comments
Under Submission