BriefGPT.xyz
Jan, 2017
k*-最近邻居: 从全局到局部
k*-Nearest Neighbors: From Global to Local
HTML
PDF
Oren Anava, Kfir Y. Levy
TL;DR
本文提出了一种简单的，能够使权重最优化的局部加权回归/分类方法，并能够为需要估计值的每个数据点高效地找到权重和最优化的邻居数量，从而在多个数据集上展示了比标准局部加权方法更优异的性能表现。
Abstract
The
weighted k-nearest neighbors algorithm
is one of the most fundamental non-parametric methods in pattern recognition and machine learning. The question of setting the
optimal number of neighbors
as well as the
→