TL;DR在 Ma 和 Chen 引入的模型的基础上,本文提出了一种两阶段的算法来处理矩阵填充中的观测偏差,并利用共享信息来提高预测性能,经实验证明本算法的表现可与未观测协变量相同,并获得性能提高。
Abstract
We consider a variant of matrix completion where entries are revealed in a
biased manner, adopting a model akin to that introduced by Ma and Chen. Instead
of treating this observation bias as a disadvantage, as i