Structural Conditions for Projection-Cost Preservation via Randomized Matrix Multiplication
Machine Learning
2018-08-21 v2 Machine Learning
Abstract
Projection-cost preservation is a low-rank approximation guarantee which ensures that the cost of any rank- projection can be preserved using a smaller sketch of the original data matrix. We present a general structural result outlining four sufficient conditions to achieve projection-cost preservation. These conditions can be satisfied using tools from the Randomized Linear Algebra literature.
Cite
@article{arxiv.1705.10102,
title = {Structural Conditions for Projection-Cost Preservation via Randomized Matrix Multiplication},
author = {Agniva Chowdhury and Jiasen Yang and Petros Drineas},
journal= {arXiv preprint arXiv:1705.10102},
year = {2018}
}
Comments
16 pages