TY - GEN
T1 - Estimation of intrinsic dimensionality using high-rate vector quantization
AU - Raginsky, Maxim
AU - Lazebnik, Svetlana
PY - 2005
Y1 - 2005
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=72349089295&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=72349089295&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:72349089295
SN - 9780262232531
T3 - Advances in Neural Information Processing Systems
SP - 1105
EP - 1112
BT - Advances in Neural Information Processing Systems 18 - Proceedings of the 2005 Conference
T2 - 2005 Annual Conference on Neural Information Processing Systems, NIPS 2005
Y2 - 5 December 2005 through 8 December 2005
ER -