Direct Estimation of Information Divergence Using Nearest Neighbor Ratios

Abstract

We propose a direct estimation method for Rényi and f-divergence measures based on a new graph theoretical interpretation. Suppose that we are given two sample sets $X$ and $Y$, respectively with $N$ and $M$ samples, where $\eta :=M/N$ is a constant value. Considering the $k$-nearest neighbor ($k$-NN) graph of $Y$ in the joint data set $(X,Y)$, we show that the average powered ratio of the number of $X$ points to the number of $Y$ points among all $k$-NN points is proportional to Rényi divergence of $X$ and $Y$ densities. A similar method can also be used to estimate f-divergence measures. We derive bias and variance rates, and show that for the class of $\gamma$-Hölder smooth functions, the estimator achieves the MSE rate of $O(N^{-2\gamma /(\gamma +d)})$. Furthermore, by using a weighted ensemble estimation technique, for density functions with continuous and bounded derivatives of up to the order $d$, and some extra conditions at the support set boundary, we derive an ensemble estimator that achieves the parametric MSE rate of $O(1/N)$. Our estimators are more computationally tractable than other competing estimators, which makes them appealing in many practical applications.

2017 IEEE International Symposium on Information Theory (ISIT)

References in corpus (1)

• Ensemble estimation of multivariate f-divergence

Cited by in corpus (4)

• Ensemble Estimation of Generalized Mutual Information with Applications to Genomics
• Geometric Estimation of Multivariate Dependency
• Nearest neighbor density functional estimation from inverse Laplace transform
• Quantifying dependencies for sensitivity analysis with multivariate input sample data