The linear time MMD implements a nonparametric statistical hypothesis test to reject the null hypothesis that to distributions p and q, each only observed via n samples, are the same, i.e. H0 : p = q.
The (unbiased) statistic is given by
See gretton2012kernel
for a detailed introduction.
Imagine we have samples from p and p. We create CDenseFeatures (here 64 bit floats aka RealFeatures)as
linear_time_mmd.sg:create_features
We create an instance of CLinearTimeMMD
, passing it data and the kernel to use, a CGaussianKernel
here.
linear_time_mmd.sg:create_instance
Computing the statistic is done as
linear_time_mmd.sg:estimate_mmd
We can perform the hypothesis test as
linear_time_mmd.sg:perform_test
../../references.bib