Multidimensional covariance function base.
It is expected that the covariance function is symmetric with respect to its arguments. The derivative is then antisymmetric.
Subclassed by o2scl::mcovar_funct_quad_correl< vec_t, vec2_t >, o2scl::mcovar_funct_rbf_noise< vec_t, vec2_t >
Public Functions
-
virtual size_t get_n_params() = 0
Get the number of parameters.
-
virtual void set_params(const ubvector &p) = 0
Set the parameters.
-
virtual double operator()(const vec_t &x1, const vec2_t &x2) = 0
The covariance function.
-
virtual double covar(const vec_t &x1, const vec_t &x2) = 0
The covariance function.
-
virtual double covar2(const vec2_t &x1, const vec2_t &x2) = 0
The covariance function.
-
virtual double deriv(const vec_t &x1, const vec2_t &x2, size_t ix) = 0
The derivative of the covariance function with respect to the first argument.
-
virtual double deriv2(const vec_t &x1, const vec2_t &x2, size_t ix, size_t iy) = 0
The second derivative of the covariance function with respect to the first argument.