English

Discrete minimax estimation with trees

Statistics Theory 2019-07-01 v3 Machine Learning Statistics Theory

Abstract

We propose a simple recursive data-based partitioning scheme which produces piecewise-constant or piecewise-linear density estimates on intervals, and show how this scheme can determine the optimal L1L_1 minimax rate for some discrete nonparametric classes.

Keywords

Cite

@article{arxiv.1812.06063,
  title  = {Discrete minimax estimation with trees},
  author = {Luc Devroye and Tommy Reddad},
  journal= {arXiv preprint arXiv:1812.06063},
  year   = {2019}
}
R2 v1 2026-06-23T06:42:54.155Z