On the concentration of the missing mass

Research output: Contribution to journalArticlepeer-review

44 Scopus citations

Abstract

A random variable is sampled from a discrete distribution. The missing mass is the probability of the set of points not observed in the sample. We sharpen and simplify McAllester and Ortiz's results (JMLR, 2003) bounding the probability of large deviations of the missing mass. Along the way, we refine and rigorously prove a fundamental inequality of Kearns and Saul (UAI, 1998).

Original languageEnglish
Pages (from-to)1-7
JournalElectronic Communications in Probability
Volume18
Issue number3
DOIs
StatePublished - 9 Jan 2013

Keywords

  • Concentration
  • Hoeffding inequality
  • Missing mass

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Fingerprint

Dive into the research topics of 'On the concentration of the missing mass'. Together they form a unique fingerprint.

Cite this