Concentration inequalities for random fields via coupling

Research output: Contribution to journalReview articlepeer-review

Abstract

We present a new and simple approach to concentration inequalities in the context of dependent random processes and random fields. Our method is based on coupling and does not use information inequalities. In case one has a uniform control on the coupling, one obtains exponential concentration inequalities. If such a uniform control is no more possible, then one obtains polynomial or stretched-exponential concentration inequalities. Our abstract results apply to Gibbs random fields, both at high and low temperatures and in particular to the low-temperature Ising model which is a concrete example of non-uniformity of the coupling.

Original languageEnglish
Pages (from-to)201-225
Number of pages25
JournalProbability Theory and Related Fields
Volume137
Issue number1-2
DOIs
Publication statusPublished - 1 Jan 2007

Keywords

  • Exponential concentration
  • Gibbs random fields
  • Ising model
  • Kantorovich-Rubinstein theorem
  • Luxembourg norm
  • Moment inequality
  • Orlicz space
  • Stretched-exponential concentration

Fingerprint

Dive into the research topics of 'Concentration inequalities for random fields via coupling'. Together they form a unique fingerprint.

Cite this