ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1402.2966
129
92
v1v2 (latest)

Nonparametric Estimation of Renyi Divergence and Friends

12 February 2014
A. Krishnamurthy
Kirthevasan Kandasamy
Barnabás Póczós
Larry A. Wasserman
ArXiv (abs)PDFHTML
Abstract

We consider nonparametric estimation of L_2, Renyi-α\alphaα and Tsallis-α\alphaα divergences of continuous distributions. Our approach is to construct estimators for particular integral functionals of two densities and translate them into divergence estimators. For the integral functionals, our estimators are based on corrections of a preliminary plug-in estimator. We analyze the rates of convergence for our estimators and show that the parametric rate of n−1/2n^{-1/2}n−1/2 is achievable when the densities' smoothness s are both at least d/4d/4d/4 where ddd is the dimension. We also derive minimax lower bounds for this problem which confirm that s>d/4s > d/4s>d/4 is necessary to achieve the n−1/2n^{-1/2}n−1/2 rate of convergence. We confirm our theoretical guarantees with a number of simulations.

View on arXiv
Comments on this paper