17
1

Minimax Optimal Additive Functional Estimation with Discrete Distribution

Abstract

This paper addresses a problem of estimating an additive functional given nn i.i.d. samples drawn from a discrete distribution P=(p1,...,pk)P=(p_1,...,p_k) with alphabet size kk. The additive functional is defined as θ(P;ϕ)=i=1kϕ(pi)\theta(P;\phi)=\sum_{i=1}^k\phi(p_i) for a function ϕ\phi, which covers the most of the entropy-like criteria. The minimax optimal risk of this problem has been already known for some specific ϕ\phi, such as ϕ(p)=pα\phi(p)=p^\alpha and ϕ(p)=plnp\phi(p)=-p\ln p. However, there is no generic methodology to derive the minimax optimal risk for the additive function estimation problem. In this paper, we reveal the property of ϕ\phi that characterizes the minimax optimal risk of the additive functional estimation problem; this analysis is applicable to general ϕ\phi. More precisely, we reveal that the minimax optimal risk of this problem is characterized by the divergence speed of the function ϕ\phi.

View on arXiv
Comments on this paper