|
CMP++: Uncertainty Quantification & Bayesian Calibration
|
Abstract base class for Gaussian Process prior mean functions. More...
#include <mean++.h>

Public Member Functions | |
| virtual | ~Mean ()=default |
| virtual double | eval (const Eigen::VectorXd &x, const Eigen::VectorXd &par) const =0 |
| virtual double | evalGradient (const Eigen::VectorXd &x, const Eigen::VectorXd &par, const size_t &i) const =0 |
| virtual double | evalHessian (const Eigen::VectorXd &x, const Eigen::VectorXd &par, const size_t &i, const size_t &j) const =0 |
Abstract base class for Gaussian Process prior mean functions.
Mathematical Formulation The mean function \(m: \mathbb{R}^D \to \mathbb{R}\) defines the expected value of the GP prior at any input \(\mathbf{x}\):
\[ m(\mathbf{x}) = \mathbb{E}[f(\mathbf{x})] \]
Commonly configured as a constant \(m(\mathbf{x}) = c\) or zero \(m(\mathbf{x}) = 0\).
Implementation Algorithm Provides virtual interfaces for mean evaluations (eval), first-order gradients (evalGradient) with respect to a parameter \(p_i\), and second-order Hessians (evalHessian).
|
virtualdefault |
|
pure virtual |
Implemented in cmp::mean::Constant, cmp::mean::Zero, and cmp::mean::ModelClusterMean.
|
pure virtual |
Implemented in cmp::mean::Constant, cmp::mean::Zero, and cmp::mean::ModelClusterMean.
|
pure virtual |
Implemented in cmp::mean::Constant, cmp::mean::Zero, and cmp::mean::ModelClusterMean.