加载中…
We study the estimation of relative entropy when is known. We show that the Cramér-Rao type bound equals the relative varentropy. Our estimator attains the Cramér-Rao type bound when the dimension is fixed. It also achieves the sample complexity when the dimension increases. This sample complexity is optimal when is the completely mixed state. Also, it has time complexity . Our proposed estimator unifiedly works under both settings.

生成讲解博客的中文版本

生成AI智能校验的中文版本