Estimation of intrinsic dimensionality using high-rate vector quantization

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We introduce a technique for dimensionality estimation based on the notion of quantization dimension, which connects the asymptotic optimal quantization error for a probability distribution on a manifold to its intrinsic dimension. The definition of quantization dimension yields a family of estimation algorithms, whose limiting case is equivalent to a recent method based on packing numbers. Using the formalism of high-rate vector quantization, we address issues of statistical consistency and analyze the behavior of our scheme in the presence of noise.

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems 18 - Proceedings of the 2005 Conference
Pages1105-1112
Number of pages8
StatePublished - Dec 1 2005
Event2005 Annual Conference on Neural Information Processing Systems, NIPS 2005 - Vancouver, BC, Canada
Duration: Dec 5 2005Dec 8 2005

Publication series

NameAdvances in Neural Information Processing Systems
ISSN (Print)1049-5258

Other

Other2005 Annual Conference on Neural Information Processing Systems, NIPS 2005
CountryCanada
CityVancouver, BC
Period12/5/0512/8/05

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint Dive into the research topics of 'Estimation of intrinsic dimensionality using high-rate vector quantization'. Together they form a unique fingerprint.

  • Cite this

    Raginsky, M., & Lazebnik, S. (2005). Estimation of intrinsic dimensionality using high-rate vector quantization. In Advances in Neural Information Processing Systems 18 - Proceedings of the 2005 Conference (pp. 1105-1112). (Advances in Neural Information Processing Systems).