部分信息子空间学习
Subspace Learning with Partial Information
The Hebrew University（希伯来大学）；Technion, Israel Institute of Technology（以色列理工学院）
摘要：
子空间学习的目标是找到$\mathbb{R}^d$的$k$维子空间，使得实例向量和子空间之间的期望平方距离尽可能小。在本文中，我们研究了部分信息设置的子空间学习，其中学习者只能观察每个实例向量的$r \le d$属性。我们提出了几种有效的算法，并分析了它们的样本复杂度
英文摘要：
The goal of subspace learning is to find a $k$-dimensional subspace of $\mathbb{R}^d$, such that the expected squared distance between instance vectors and the subspace is as small as possible. In this paper we study subspace learning in a partial information setting, in which the learner can only observe $r \le d$ attributes from each instance vector. We propose several efficient algorithms for this task, and analyze their sample complexity
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
