lnn_mi: Local Nearest Neighbor (LNN) MI Estimator

In rmi: Mutual Information Estimators

Description

Local Nearest Neighbor (LNN) mutual information estimator by Gao et al. 2017. This estimator uses the LNN entropy (lnn_entropy) estimator into the mutual information identity.

Usage

lnn_mi(data, splits, k = 5, tr = 30)

Arguments

data	Matrix of sample observations, each row is an observation.
splits	A vector that describes which sets of columns in data to compute the mutual information between. For example, to compute mutual information between two variables use splits = c(1,1). To compute redundancy among multiple random variables use splits = rep(1,ncol(data)). To compute the mutual information between two random vector list the dimensions of each vector.
k	Order of the local kNN bandwidth selection.
tr	Order of truncation (number of neighbors to include in the local density estimation).

References

Gao, W., Oh, S., & Viswanath, P. (2017). Density functional estimators with k-nearest neighbor bandwidths. IEEE International Symposium on Information Theory - Proceedings, 1, 1351–1355.

Examples

set.seed(123)
x <- rnorm(1000)
y <- x + rnorm(1000)
lnn_mi(cbind(x,y),c(1,1))

rmi documentation built on May 2, 2019, 3:27 a.m.