Date of Original Version



Conference Proceeding

Rights Management

Copyright 2015 by the authors

Abstract or Description

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 √n-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-Ess\'{e}en style inequality characterizing the rate of convergence to normality. We also show that this estimator is minimax optimal.



Published In

Journal of Machine Learning Research : Workshop and Conference Proceedings, 38, 498-506.