This function is called by fit.ssm to compute the coefficient
vector that interpolates the data and minimises the smoothness of the
resulting model.
find.theta(response, K, design_model, tol = .Machine$double.eps)An length \(n\) vector. The observed responses.
A semi-positive definite \(N x N\) matrix that defines the smoothing criterion.
The \(n x N\) design model matrix.
(optional) The model fitting requires the inversion of a large
matrix and if the model basis is too large there can be numerical issues.
This argument is passed on to solve so models can be fit
despite these issues.
A vector of parameters of length \(N\) if the model is fit
successfully. NA is returned should solve not invert
the required matrix.