On Identifying a Massive Number of Distributions
arXiv:1801.04593 · doi:10.1109/ISIT.2018.8437586
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 $n$. Asymptotically matching upper and lower bounds on the probability of error are derived.
Under Submission