License: Creative Commons Attribution 3.0 Unported license (CC-BY 3.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.APPROX-RANDOM.2018.4
URN: urn:nbn:de:0030-drops-94087
URL: https://drops.dagstuhl.de/opus/volltexte/2018/9408/
Go to the corresponding LIPIcs Volume Portal


Bhaskara, Aditya ; Kumar, Srivatsan

Low Rank Approximation in the Presence of Outliers

pdf-format:
LIPIcs-APPROX-RANDOM-2018-4.pdf (0.5 MB)


Abstract

We consider the problem of principal component analysis (PCA) in the presence of outliers. Given a matrix A (d x n) and parameters k, m, the goal is to remove a set of at most m columns of A (outliers), so as to minimize the rank-k approximation error of the remaining matrix (inliers). While much of the work on this problem has focused on recovery of the rank-k subspace under assumptions on the inliers and outliers, we focus on the approximation problem. Our main result shows that sampling-based methods developed in the outlier-free case give non-trivial guarantees even in the presence of outliers. Using this insight, we develop a simple algorithm that has bi-criteria guarantees. Further, unlike similar formulations for clustering, we show that bi-criteria guarantees are unavoidable for the problem, under appropriate complexity assumptions.

BibTeX - Entry

@InProceedings{bhaskara_et_al:LIPIcs:2018:9408,
  author =	{Aditya Bhaskara and Srivatsan Kumar},
  title =	{{Low Rank Approximation in the Presence of Outliers}},
  booktitle =	{Approximation, Randomization, and Combinatorial  Optimization. Algorithms and Techniques (APPROX/RANDOM 2018)},
  pages =	{4:1--4:16},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-085-9},
  ISSN =	{1868-8969},
  year =	{2018},
  volume =	{116},
  editor =	{Eric Blais and Klaus Jansen and Jos{\'e} D. P. Rolim and David Steurer},
  publisher =	{Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2018/9408},
  URN =		{urn:nbn:de:0030-drops-94087},
  doi =		{10.4230/LIPIcs.APPROX-RANDOM.2018.4},
  annote =	{Keywords: Low rank approximation, PCA, Robustness to outliers}
}

Keywords: Low rank approximation, PCA, Robustness to outliers
Collection: Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2018)
Issue Date: 2018
Date of publication: 13.08.2018


DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI