BriefGPT.xyz
Jun, 2012
算子模型中局部损失优化：光谱学习的新视角
Local Loss Optimization in Operator Models: A New Insight into Spectral Learning
HTML
PDF
Borja Balle, Ariadna Quattoni, Xavier Carreras
TL;DR
本文重新审视了用于学习拉丁变量模型的谱方法，并给出了新的视角。通过在有限子集上定义目标函数，该方法被推广为一种类谱优化方法，并发现连续正则化参数允许更好地平衡模型的准确性和复杂度，同时证明了随机选择本地损失函数的普遍有效性。
Abstract
This paper re-visits the
spectral method
for learning
latent variable models
defined in terms of observable operators. We give a new perspective on the method, showing that operators can be recovered by minimizin
→