BriefGPT.xyz
Jun, 2013
R3MC: 一种用于低秩矩阵补全的黎曼三因子算法
R3MC: A Riemannian three-factor algorithm for low-rank matrix completion
HTML
PDF
B. Mishra, R. Sepulchre
TL;DR
利用流形上的黎曼优化框架开发了一种名为 R3MC 的非线性共轭梯度方法,用于低秩矩阵完成,通过比较实验我们发现 R3MC 在不同问题实例中表现出优异的性能,特别是在结合了稀疏采样和病态数据后表现出色。
Abstract
We exploit the versatile framework of
riemannian optimization
on quotient manifolds to implement R3MC, a nonlinear conjugate gradient method optimized for
matrix completion
. The underlying geometry uses a Riemann
→