Escaping the curse of dimensionality with a tree-based regressor

Samory Kpotufe

Research output: Contribution to conferencePaperpeer-review

13 Scopus citations


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 - 2009
Event22nd Conference on Learning Theory, COLT 2009 - Montreal, QC, Canada
Duration: Jun 18 2009Jun 21 2009


Other22nd Conference on Learning Theory, COLT 2009
CityMontreal, QC

All Science Journal Classification (ASJC) codes

  • Education

Cite this