NeurIPS 2020

Optimal Prediction of the Number of Unseen Species with Multiplicity

Meta Review

This paper studies a variant of Fisher et al's unseen species problem, namely, predicting the number of new symbols that appears at least \mu times in the future (unobserved) sample of size a \times n on the basis of the existing sample of size n. A minimax optimal strategy (up to a constant factor) with corresponding upper and lower bounds are presented for this problem.