Escaping the curse of dimensionality with a tree-based regressor

Samory Kpotufe

Research output: Contribution to conferencePaper

10 Scopus citations

Abstract

We present the first tree-based regressor whose convergence rate depends only on the intrinsic dimension of the data, namely its Assouad dimension. The regressor uses the RPtree partitioning procedure, a simple randomized variant of k-d trees.

Original languageEnglish (US)
StatePublished - Dec 1 2009
Event22nd Conference on Learning Theory, COLT 2009 - Montreal, QC, Canada
Duration: Jun 18 2009Jun 21 2009

Other

Other22nd Conference on Learning Theory, COLT 2009
CountryCanada
CityMontreal, QC
Period6/18/096/21/09

All Science Journal Classification (ASJC) codes

  • Education

Cite this

Kpotufe, S. (2009). Escaping the curse of dimensionality with a tree-based regressor. Paper presented at 22nd Conference on Learning Theory, COLT 2009, Montreal, QC, Canada.