License: Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.APPROX/RANDOM.2021.49
URN: urn:nbn:de:0030-drops-147422
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2021/14742/
Go to the corresponding LIPIcs Volume Portal

Parulekar, Aditya ; Parulekar, Advait ; Price, Eric

L1 Regression with Lewis Weights Subsampling

pdf-format:
LIPIcs-APPROX49.pdf (0.8 MB)

Abstract

We consider the problem of finding an approximate solution to ?₁ regression while only observing a small number of labels. Given an n × d unlabeled data matrix X, we must choose a small set of m ≪ n rows to observe the labels of, then output an estimate β̂ whose error on the original problem is within a 1 + ε factor of optimal. We show that sampling from X according to its Lewis weights and outputting the empirical minimizer succeeds with probability 1-δ for m > O(1/(ε²) d log d/(ε δ)). This is analogous to the performance of sampling according to leverage scores for ?₂ regression, but with exponentially better dependence on δ. We also give a corresponding lower bound of Ω(d/(ε²) + (d + 1/(ε²)) log 1/(δ)).

BibTeX - Entry

@InProceedings{parulekar_et_al:LIPIcs.APPROX/RANDOM.2021.49,
  author =	{Parulekar, Aditya and Parulekar, Advait and Price, Eric},
  title =	{{L1 Regression with Lewis Weights Subsampling}},
  booktitle =	{Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2021)},
  pages =	{49:1--49:21},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-207-5},
  ISSN =	{1868-8969},
  year =	{2021},
  volume =	{207},
  editor =	{Wootters, Mary and Sanit\`{a}, Laura},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2021/14742},
  URN =		{urn:nbn:de:0030-drops-147422},
  doi =		{10.4230/LIPIcs.APPROX/RANDOM.2021.49},
  annote =	{Keywords: Active regression, Lewis weights}
}

Keywords: Active regression, Lewis weights
Collection: Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2021)
Issue Date: 2021
Date of publication: 15.09.2021

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