Gaussian distribution¶
- class pints.toy.GaussianLogPDF(mean=[0, 0], sigma=[1, 1])[source]¶
Toy distribution based on a multivariate (unimodal) Normal/Gaussian distribution.
Extends
pints.toy.ToyLogPDF
.- Parameters:
mean – The distribution mean (specified as a vector).
sigma – The distribution’s covariance matrix. Can be given as either a matrix or a vector (in which case
diag(sigma)
will be used. Should be symmetric and positive-semidefinite.
- distance(samples)[source]¶
Returns the
Kullback-Leibler divergence
.
- kl_divergence(samples)[source]¶
Calculates the Kullback-Leibler divergence between a given list of samples and the distribution underlying this LogPDF.
The returned value is (near) zero for perfect sampling, and then increases as the error gets larger.
See: https://en.wikipedia.org/wiki/Kullback-Leibler_divergence
- suggested_bounds()¶
Returns suggested boundaries for prior.