Indexability, concentration, and VC theory

Details Indexability, concentration, and VC theory Indexability, concentration, and VC theory

2010-08-30

arxiv.org/abs/1008.5105v5

J. Discrete Algorithms 13 (2012), pp. 2-18

Computer Science

Data Structures and Algorithms

17 pages, final submission to J. Discrete Algorithms (an expanded, improved and corrected version of the SISAP'2010 invited pa

Scientific paper

10.1016/j.jda.2011.10.002

Degrading performance of indexing schemes for exact similarity search in high dimensions has long since been linked to histograms of distributions of distances and other 1-Lipschitz functions getting concentrated. We discuss this observation in the framework of the phenomenon of concentration of measure on the structures of high dimension and the Vapnik-Chervonenkis theory of statistical learning.

Affiliated with

Also associated with

No associations

Rating

Indexability, concentration, and VC theory does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Indexability, concentration, and VC theory, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Indexability, concentration, and VC theory will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-401048