A Normal distribution over matrices
A Normal distribution over matrices
the location of the distribution
the variance of the rows
the variance of the columns
This class learns a correlated system matrix using the InverseWishart prior on the system noise matrix
The particle filter can be used for inference of Dynamic Generalised Linear Models (DGLMs), where the observation distribution is not Gaussian.
Particle Gibbs Sampler for A Dynamic Generalised Linear Model
Particle Gibbs with Ancestor Sampling Requires a Tractable state evolution kernel
Utility class for parallelism and IO
Perform the Kalman Filter by updating the value of the Singular Value Decomp.
Perform the Kalman Filter by updating the value of the Singular Value Decomp. of the state covariance matrix, C = UDU^T https://arxiv.org/pdf/1611.03686.pdf
Backward Sampler utilising the SVD for stability TODO: Check this
A Gaussian DLM can be implicitly converted to a DGLM Then particle filtering methods can be used on Gaussian Models