English

Minimax Optimal Additive Functional Estimation with Discrete Distribution

Information Theory 2018-12-04 v1 math.IT Statistics Theory Statistics Theory

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.

Cite

@article{arxiv.1812.00001,
  title  = {Minimax Optimal Additive Functional Estimation with Discrete Distribution},
  author = {Kazuto Fukuchi and Jun Sakuma},
  journal= {arXiv preprint arXiv:1812.00001},
  year   = {2018}
}

Comments

This paper was presented in part at the 2017 IEEE International Symposium on Information Theory (ISIT), Aachen, Germany and 2018 IEEE International Symposium on Information Theory (ISIT), Vail, USA. arXiv admin note: text overlap with arXiv:1801.05362

R2 v1 2026-06-23T06:27:23.617Z