On Semi-Supervised Estimation of Distributions

Autor:	Erol, H. S. Melihcan, Sula, Erixhen, Zheng, Lizhong
Rok vydání:	2023
Předmět:	Mathematics - Statistics Theory Computer Science - Information Theory
Druh dokumentu:	Working Paper
Popis:	We study the problem of estimating the joint probability mass function (pmf) over two random variables. In particular, the estimation is based on the observation of $m$ samples containing both variables and $n$ samples missing one fixed variable. We adopt the minimax framework with $l^p_p$ loss functions, and we show that the composition of uni-variate minimax estimators achieves minimax risk with the optimal first-order constant for $p \ge 2$, in the regime $m = o(n)$. Comment: Presented in ISIT-2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2305.07955 Zobrazit plný text záznamu View this record from Arxiv