We analyze the Kozachenko-Leonenko (KL) fixed k-nearest neighbor estimator for the differential entropy. We obtain the first uniform upper bound on its performance for any fixed k over Hölder balls on a torus without assuming any conditions on how close the density could be from zero. Accompanying a recent minimax lower bound over the Hölder ball, we show that the KL estimator for any fixed k 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.

Neural Information Processing Systems http://nips.cc/

We analyze the Kozachenko-Leonenko (KL) fixed k-nearest neighbor estimator for the differential entropy. We obtain the first uniform upper bound on its performance for any fixed k over Hölder balls on a torus without assuming any conditions on how close the density could be from zero. Accompanying a recent minimax lower bound over the Hölder ball, we show that the KL estimator for any fixed k 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.

Entropy estimation is one of the prototypical problems in distribution property testing.