|
HLIBpro 3.1
|
Matern covariance coefficient function. More...
#include <TMaternCovCoeffFn.hh>
Public Member Functions | |
| TMaternCovCoeffFn (const value_t sigma, const value_t length, const value_t nu, const std::vector< point_t > &vertices) | |
| virtual void | eval (const std::vector< idx_t > &rowidxs, const std::vector< idx_t > &colidxs, value_t *matrix) const |
| virtual matform_t | matrix_format () const |
Public Member Functions inherited from TCoeffFn< T > | |
| TCoeffFn () | |
| default constructor | |
| virtual | ~TCoeffFn () |
| destructor | |
| virtual void | eval (const TIndexSet &rowis, const TIndexSet &colis, value_t *matrix) const |
| virtual void | eval (const std::vector< idx_t > &tau, const std::vector< idx_t > &sigma, value_t *matrix) const =0 |
TMaternCovCoeffFn implements the Matern covarience kernel
\f[ C(h, \theta ) := \frac{\sigma^2}{2^{\nu-1} \Gamma(\nu)} \left(\frac{h}{\ell}\right)^{\nu} K_{\nu}\left(\frac{h}{\ell}\right) \f]
with \f$\theta=(\sigma,\ell,\nu)\f$, where \f$\sigma\f$ is the variance; \f$\nu > 0\f$ controls
the smoothness of the random field, with larger values of corresponding to smoother fields;
and \f$\ell\f$ is a spatial range parameter that measures how quickly the correlation of the
random field decays with distance.
| TMaternCovCoeffFn | ( | const value_t | sigma, |
| const value_t | length, | ||
| const value_t | nu, | ||
| const std::vector< point_t > & | vertices | ||
| ) |
constructor
|
virtual |
coefficient evaluation
return format of matrix, e.g. symmetric or hermitian
Reimplemented from TCoeffFn< T >.