11
9

Near-optimal estimation of the unseen under regularly varying tail populations

Abstract

Given nn samples from a population of individuals belonging to different species, what is the number UU of hitherto unseen species that would be observed if λn\lambda n new samples were collected? This is an important problem in many scientific endeavors, and it has been the subject of recent works introducing non-parametric estimators of UU that are minimax near-optimal and consistent all the way up to λlogn\lambda \asymp\log n. These works do not rely on any assumption on the underlying unknown distribution pp of the population, and therefore, while providing a theory in its greatest generality, worst-case distributions may severely hamper the estimation of UU in concrete applications. In this paper, we consider the problem of strengthening the non-parametric framework for estimating UU. Inspired by the estimation of rare probabilities in extreme value theory, and motivated by the ubiquitous power-law type distributions in many natural and social phenomena, we make use of a semi-parametric assumption regular variation of index α(0,1)\alpha \in (0,1) for the tail behaviour of pp. Under this assumption, we introduce an estimator of UU that is simple, linear in the sampling information, computationally efficient, and scalable to massive datasets. Then, uniformly over our class of regularly varying tail distributions, we show that the proposed estimator has provable guarantees: i) it is minimax near-optimal, up to a power of logn\log n factor; ii) it is consistent all of the way up to logλnα/2/logn\log\lambda \asymp n^{\alpha/2}/\sqrt{\log n}, and this range is the best possible. This work presents the first study on the estimation of the unseen under regularly varying tail distributions. A numerical illustration of our methodology is presented for synthetic data and real data.

View on arXiv
Comments on this paper