BriefGPT.xyz
Jun, 2013
高维稀疏高斯混合模型的极小极大理论
Minimax Theory for High-dimensional Gaussian Mixtures with Sparse Mean Separation
HTML
PDF
Martin Azizyan, Aarti Singh, Larry Wasserman
TL;DR
本文提供了在高维情况下学习高斯混合物的准确最小值界限和基本限制，研究表明，如果存在决定均值分离的随机维度的稀疏子集，则样本复杂度只取决于相关维度的数量和平均分离，可通过简单的计算有效过程来实现；结果为最近结合特征选择和聚类的方法提供了理论基础的第一步。
Abstract
While several papers have investigated computationally and statistically efficient methods for learning
gaussian mixtures
, precise
minimax bounds
for their statistical performance as well as fundamental limits in
→