A Randomized Rounding Algorithm for Sparse PCA
Data Structures and Algorithms
2016-11-24 v5 Machine Learning
Machine Learning
Abstract
We present and analyze a simple, two-step algorithm to approximate the optimal solution of the sparse PCA problem. Our approach first solves a L1 penalized version of the NP-hard sparse PCA optimization problem and then uses a randomized rounding strategy to sparsify the resulting dense solution. Our main theoretical result guarantees an additive error approximation and provides a tradeoff between sparsity and accuracy. Our experimental evaluation indicates that our approach is competitive in practice, even compared to state-of-the-art toolboxes such as Spasm.
Cite
@article{arxiv.1508.03337,
title = {A Randomized Rounding Algorithm for Sparse PCA},
author = {Kimon Fountoulakis and Abhisek Kundu and Eugenia-Maria Kontopoulou and Petros Drineas},
journal= {arXiv preprint arXiv:1508.03337},
year = {2016}
}
Comments
28 pages, 11 figures, 2 tables