The Nearest Neighbor Information Estimator is Adaptively Near Minimax Rate-Optimal

11/23/2017
by   Jiantao Jiao, et al.
0

We analyze the Kozachenko--Leonenko (KL) nearest neighbor estimator for the differential entropy. We obtain the first uniform upper bound on its performance over Hölder balls on a torus without assuming any conditions on how close the density could be from zero. Accompanying a new minimax lower bound over the Hölder ball, we show that the KL estimator is achieving the minimax rates up to logarithmic factors without cognizance of the smoothness parameter s of the Hölder ball for s∈ (0,2] and arbitrary dimension d, rendering it the first estimator that provably satisfies this property.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset