Sublinear Time Algorithms for Earth Mover's Distance

Khanh Do Ba, Huy L. Nguyen, Huy N. Nguyen, Ronitt Rubinfeld

Research output: Contribution to journalArticlepeer-review

24 Scopus citations

Abstract

We study the problem of estimating the Earth Mover's Distance (EMD) between probability distributions when given access only to samples of the distribution. We give closeness testers and additive-error estimators over domains in [0,1]d, with sample complexities independent of domain size-permitting the testability even of continuous distributions over infinite domains. Instead, our algorithms depend on the dimension of the domain space and the quality of the result required. We also prove lower bounds for closeness testing, showing the dependencies on these parameters to be essentially optimal. Additionally, we consider whether natural classes of distributions exist for which there are algorithms with better dependence on the dimension, and show that for highly clusterable data, this is indeed the case. Lastly, we consider a variant of the EMD, defined over tree metrics instead of the usual ℓ1 metric, and give tight upper and lower bounds.

Original languageEnglish
Pages (from-to)428-442
Number of pages15
JournalTheory of Computing Systems
Volume48
Issue number2
DOIs
StatePublished - Feb 2011
Externally publishedYes

Keywords

  • Earth Mover's Distance
  • Property testing
  • Sublinear-time algorithms

Fingerprint

Dive into the research topics of 'Sublinear Time Algorithms for Earth Mover's Distance'. Together they form a unique fingerprint.

Cite this