Detailed Description

Solver Policy 2: Cholesky decomposition of K (Covariance).

This solver pre-computes the Cholesky factorization of the prior covariance matrix Sigma = K_root * K_root^T. The system matrix becomes B = I + K_root^T * W * K_root, which is factorized in each iteration.

This approach is numerically more stable than Solver 1 when the covariance matrix has a more complex structure.

Note: This solver corresponds to solver == 2 in the original code.

Definition at line 709 of file laplace_marginal_density_estimator.hpp.

#include <laplace_marginal_density_estimator.hpp>

Public Member Functions
template<typename NewtonStateT , typename CovarMat >
	CholeskyKSolver (const NewtonStateT &state, const CovarMat &covariance)

template<typename NewtonStateT , typename LLFun , typename LLTupleArgs , typename CovarMat >
void	solve_step (NewtonStateT &state, const LLFun &ll_fun, const LLTupleArgs &ll_args, const CovarMat &covariance, int hessian_block_size, std::ostream *msgs)
	Perform one Newton step using covariance Cholesky solver.

double	compute_log_determinant () const
	Compute log determinant of B from Cholesky factor.

template<typename NewtonStateT >
auto	build_result (NewtonStateT &state, double log_det)
	Build the final result structure.

Public Attributes
Eigen::MatrixXd	K_root
	Lower Cholesky factor of covariance: Sigma = K_root * K_root^T.

Eigen::SparseMatrix< double >	W_full
	Full (block) Hessian matrix from likelihood.

Eigen::LLT< Eigen::MatrixXd >	llt_B
	Cholesky factorization of B = I + K_root^T * W * K_root.

The documentation for this struct was generated from the following file:

stan/math/mix/functor/laplace_marginal_density_estimator.hpp

Detailed Description

Public Member Functions

Public Attributes