Use second Kraskov algorithm to compute mutual information
Specification
Alias: None
Arguments: None
Description
This algorithm is derived in [KStogbauerG04] . The mutual information between
random variables is approximated by
where is the digamma function, is the number of nearest
neighbors being used, and is the
number of samples available for the joint distribution of the random variables.
For each point in the joint
distribution, and its nearest neighbors are projected into
each marginal subpsace. For each subspace ,
is defined as the radius of the -ball
containing all points. Then, is the number of points
in the -th subspace within a distance of from the
point . The angular brackets denote that the average of
is taken over all points .
Sandia National Laboratories is a multimission laboratory managed and operated by National Technology and Engineering Solutions of Sandia, LLC., a wholly owned subsidiary of Honeywell International, Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA-0003525.