BriefGPT.xyz
Feb, 2020
重尾分布的私有均值估计
Private Mean Estimation of Heavy-Tailed Distributions
HTML
PDF
Gautam Kamath, Vikrant Singhal, Jonathan Ullman
TL;DR
本文给出了关于有边界k阶矩分布不同隐私均值估计的最小最大样本复杂度的上下界，包括单变量和多变量情况，通过研究发现具有差分隐私约束时的样本复杂度与没有隐私时不同。
Abstract
We give new upper and lower bounds on the minimax
sample complexity
of differentially private
mean estimation
of distributions with bounded $k$-th moments. Roughly speaking, in the
→