Column Selection via Adaptive Sampling

Abstract

Selecting a good column (or row) subset of massive data matrices has found many applications in data analysis and machine learning. We propose a new adaptive sampling algorithm that can be used to improve any relative-error column selection algorithm. Our algorithm delivers a tighter theoretical bound on the approximation error which we also demonstrate empirically using two well known relative-error column subset selection algorithms. Our experimental results on synthetic and real-world data show that our algorithm outperforms non-adaptive sampling as well as prior adaptive sampling approaches.

Cite

Text

Paul et al. "Column Selection via Adaptive Sampling." Neural Information Processing Systems, 2015.

Markdown

[Paul et al. "Column Selection via Adaptive Sampling." Neural Information Processing Systems, 2015.](https://mlanthology.org/neurips/2015/paul2015neurips-column/)

BibTeX

@inproceedings{paul2015neurips-column,
  title     = {{Column Selection via Adaptive Sampling}},
  author    = {Paul, Saurabh and Magdon-Ismail, Malik and Drineas, Petros},
  booktitle = {Neural Information Processing Systems},
  year      = {2015},
  pages     = {406-414},
  url       = {https://mlanthology.org/neurips/2015/paul2015neurips-column/}
}