论文标题
强大地学习高斯人的混合物
Robust Learning of Mixtures of Gaussians
论文作者
论文摘要
我们解决了强大统计数据中的主要问题之一。特别是，如果$ x $是两种任意$ d $ d二维高斯人的均匀加权混合物，那么我们设计了一种多项式时间算法，可以从$ x $ a $ a $ a $ \ eps $ - fraction中访问样品，其中$ x $ to $ x $ to $ x $ to $ \ \ poly（\ poly（\ eps）$ \ eps $ $ \ eps $。
We resolve one of the major outstanding problems in robust statistics. In particular, if $X$ is an evenly weighted mixture of two arbitrary $d$-dimensional Gaussians, we devise a polynomial time algorithm that given access to samples from $X$ an $\eps$-fraction of which have been adversarially corrupted, learns $X$ to error $\poly(\eps)$ in total variation distance.
