English

NP-Hardness and Inapproximability of Sparse PCA

Machine Learning 2015-02-23 v2 Computational Complexity Data Structures and Algorithms Combinatorics Machine Learning

Abstract

We give a reduction from {\sc clique} to establish that sparse PCA is NP-hard. The reduction has a gap which we use to exclude an FPTAS for sparse PCA (unless P=NP). Under weaker complexity assumptions, we also exclude polynomial constant-factor approximation algorithms.

Cite

@article{arxiv.1502.05675,
  title  = {NP-Hardness and Inapproximability of Sparse PCA},
  author = {Malik Magdon-Ismail},
  journal= {arXiv preprint arXiv:1502.05675},
  year   = {2015}
}
R2 v1 2026-06-22T08:33:28.156Z