English

Multivariate f-Divergence Estimation With Confidence

Information Theory 2015-03-16 v1 math.IT Machine Learning

Abstract

The problem of f-divergence estimation is important in the fields of machine learning, information theory, and statistics. While several nonparametric divergence estimators exist, relatively few have known convergence properties. In particular, even for those estimators whose MSE convergence rates are known, the asymptotic distributions are unknown. We establish the asymptotic normality of a recently proposed ensemble estimator of f-divergence between two distributions from a finite number of samples. This estimator has MSE convergence rate of O(1/T), is simple to implement, and performs well in high dimensions. This theory enables us to perform divergence-based inference tasks such as testing equality of pairs of distributions based on empirical samples. We experimentally validate our theoretical results and, as an illustration, use them to empirically bound the best achievable classification error.

Keywords

Cite

@article{arxiv.1411.2045,
  title  = {Multivariate f-Divergence Estimation With Confidence},
  author = {Kevin R. Moon and Alfred O. Hero},
  journal= {arXiv preprint arXiv:1411.2045},
  year   = {2015}
}

Comments

20 pages, 1 figure. Accepted to NIPS 2014 (supplementary material is included in the appendices)

R2 v1 2026-06-22T06:51:52.785Z