• DOI:10.1214/19-aos1927
Corpus ID: 11886708

Optimal rates of entropy estimation over Lipschitz balls

@article{Han2017OptimalRO,
  title={Optimal rates of entropy estimation over Lipschitz balls},
  author={Y. Han and J. Jiao and T. Weissman and Y. Wu},
  journal={ArXiv},
  year={2017},
  volume={abs/1711.02141}
}

Y. Han, J. Jiao, +1 author Y. Wu

Published 2017

Mathematics, Computer Science

ArXiv

We consider the problem of minimax estimation of the entropy of a density over Lipschitz balls. Dropping the usual assumption that the density is bounded away from zero, we obtain the minimax rates $(n\ln n)^{-\frac{s}{s+d}} + n^{-1/2}$ for $0<s\leq 2$ in arbitrary dimension $d$, where $s$ is the smoothness parameter and $n$ is the number of independent samples. Using a two-stage approximation technique, which first approximate the density by its kernel-smoothed version, and then approximate… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed