Optimality of the Johnson-Lindenstrauss Dimensionality Reduction for Practical Measures

Yair Bartal*, Ora Nova Fandina*, Kasper Green Larsen*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

It is well known that the Johnson-Lindenstrauss dimensionality reduction method is optimal for worst case distortion. While in practice many other methods and heuristics are used, not much is known in terms of bounds on their performance. The question of whether the JL method is optimal for practical measures of distortion was recently raised in [8] (NeurIPS'19). They provided upper bounds on its quality for a wide range of practical measures and showed that indeed these are best possible in many cases. Yet, some of the most important cases, including the fundamental case of average distortion were left open. In particular, they show that the JL transform has 1 + ? average distortion for embedding into k-dimensional Euclidean space, where k = O(1/?2), and for more general q-norms of distortion, k = O(max(1/?2, q/?)), whereas tight lower bounds were established only for large values of q via reduction to the worst case. In this paper we prove that these bounds are best possible for any dimensionality reduction method, for any 1 = q = O(log(2??2n)) and ? = v1n, where n is the size of the subset of Euclidean space. Our results also imply that the JL method is optimal for various distortion measures commonly used in practice, such as stress, energy and relative error. We prove that if any of these measures is bounded by ? then k = ?(1/?2), for any ? = v1n, matching the upper bounds of [8] and extending their tightness results for the full range moment analysis. Our results may indicate that the JL dimensionality reduction method should be considered more often in practical applications, and the bounds we provide for its quality should be served as a measure for comparison when evaluating the performance of other methods and heuristics.

Original languageAmerican English
Title of host publication38th International Symposium on Computational Geometry, SoCG 2022
EditorsXavier Goaoc, Michael Kerber
PublisherSchloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing
Pages13:1-13:16
Number of pages16
ISBN (Electronic)9783959772273
DOIs
StatePublished - 1 Jun 2022
Event38th International Symposium on Computational Geometry, SoCG 2022 - Berlin, Germany
Duration: 7 Jun 202210 Jun 2022

Publication series

NameLeibniz International Proceedings in Informatics, LIPIcs
Volume224
ISSN (Print)1868-8969

Conference

Conference38th International Symposium on Computational Geometry, SoCG 2022
Country/TerritoryGermany
CityBerlin
Period7/06/2210/06/22

Bibliographical note

Publisher Copyright:
© Yair Bartal, Ora Nova Fandina, and Kasper Green Larsen; licensed under Creative Commons License CC-BY 4.0

Keywords

  • JL transform
  • average distortion
  • practical dimensionality reduction

Fingerprint

Dive into the research topics of 'Optimality of the Johnson-Lindenstrauss Dimensionality Reduction for Practical Measures'. Together they form a unique fingerprint.

Cite this