Subspace Learning with Partial Information

2014/02/19 by Gonen, Alon, Rosenbaum, Dan, Eldar, Yonina +1 · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1402.4844

Abstract

The goal of subspace learning is to find a k-dimensional subspace of 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 ≤ d attributes from each instance vector. We propose several efficient algorithms for this task, and analyze their sample complexity

Cited by

• Compressive Toeplitz Covariance Estimation From Few-Bit Quantized Measurements With Applications to DOA Estimation

Related

• Minimal Sample Subspace Learning: Theory and Algorithms
• Online Low-Rank Subspace Learning from Incomplete Data: A Bayesian View
• Subspace Learning from Extremely Compressed Measurements
• On the Sample Complexity of Subspace Learning
• Compressed Subspace Learning Based on Canonical Angle Preserving Property