AISTATS 2015poster15 citations

On Estimating L_2^2 Divergence

Akshay Krishnamurthy, Kirthevasan Kandasamy, Barnabas Poczos, Larry Wasserman

Abstract

We give a comprehensive theoretical characterization of a nonparametric estimator for the L_2^2 divergence between two continuous distributions. We first bound the rate of convergence of our estimator, showing that it is \sqrtn-consistent provided the densities are sufficiently smooth. In this smooth regime, we then show that our estimator is asymptotically normal, construct asymptotic confidence intervals, and establish a Berry-Esséen style inequality characterizing the rate of convergence to normality. We also show that this estimator is minimax optimal.

BibTeX
@InProceedings{pmlr-v38-krishnamurthy15,
  title = 	 {{On Estimating L_2^2 Divergence}},
  author = 	 {Krishnamurthy, Akshay and Kandasamy, Kirthevasan and Poczos, Barnabas and Wasserman, Larry},
  booktitle = 	 {Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics},
  pages = 	 {498--506},
  year = 	 {2015},
  editor = 	 {Lebanon, Guy and Vishwanathan, S. V. N.},
  volume = 	 {38},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {San Diego, California, USA},
  month = 	 {09--12 May},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v38/krishnamurthy15.pdf},
  url = 	 {https://proceedings.mlr.press/v38/krishnamurthy15.html},
  abstract = 	 {We give a comprehensive theoretical characterization of a nonparametric estimator for the L_2^2 divergence between two continuous distributions. We first bound the rate of convergence of our estimator, showing that it is \sqrtn-consistent provided the densities are sufficiently smooth. In this smooth regime, we then show that our estimator is asymptotically normal, construct asymptotic confidence intervals, and establish a Berry-Esséen style inequality characterizing the rate of convergence to normality. We also show that this estimator is minimax optimal.}
}
On Estimating L_2^2 Divergence · AISTATS 2015