On Semi-Supervised Estimation of Distributions
On Semi-Supervised Estimation of Distributions
复制标题
DOI：
10.1109/isit54713.2023.10206752
复制
发表时间：
2023-05
期刊：
影响因子：
--
通讯作者：
H. Erol;Erixhen Sula;Lizhong Zheng
中科院分区：
文献类型：
--
作者：
H. Erol;Erixhen Sula;Lizhong Zheng
研究了两个随机变量的联合概率质量函数的估计问题。特别地，估计是基于对包含两个变量的m个样本和缺失一个固定变量的n个样本的观察。我们采用了具有l_p^p$损失函数的Minimax框架，证明了在m = o（n）的情形下，当p ≥ 2时，单变量Minimax估计的组合具有最优一阶常数的Minimax风险.
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 ≥ 2, in the regime m = o(n).