LogGaussian Class Reference

Defines the log-normal probability density function. More...

#include <log_gaussian.h>

Inheritance diagram for LogGaussian:

Collaboration diagram for LogGaussian:

Public Member Functions
	LogGaussian (double mu_, double sigma_)
	Sets the default for the parameter mu to 0.0 and for the parameter sigma to 1.0.
virtual float	function (const float lambda_) const
virtual double	function (const double lambda_) const
virtual long double	function (const long double lambda_) const
Public Member Functions inherited from Function
virtual	~Function ()
	Default virtual destructor.

Public Attributes
double	mu
double	sigma

Detailed Description

Defines the log-normal probability density function.

\[ f: \lambda \mapsto \frac{1}{\lambda \sigma \sqrt{2 \pi}} e^{-\frac{1}{2} x^2}, \]

where

\[ x = \frac{\log(\lambda) - \log(\mu)}{\sigma}, \]

and \( \mu \) and \( \sigma \) parameters are the mean and standard deviation of the Gaussian function and should be set by this->mu and this->sigma members, respectively.

The matrix function \( f: \mathbb{R}^{n \times n} \to \mathbb{R}^{n \times n} \) is used in

\[ \mathrm{trace} \left( f(\mathbf{A}) \right). \]

However, instead of a matrix function, the equivalent scalar function \( f: \mathbb{R} \to \mathbb{R} \) is defiend which acts on the eigenvalues of the matrix.

Definition at line 51 of file log_gaussian.h.

Constructor & Destructor Documentation

LogGaussian()

LogGaussian::LogGaussian	(	double	mu_,
		double	sigma_
	)

Sets the default for the parameter mu to 0.0 and for the parameter sigma to 1.0.

Definition at line 34 of file log_gaussian.cpp.

{
    this->mu = mu_;
    this->sigma = sigma_;
}

References mu, and sigma.

Member Function Documentation

function() [1/3]

double LogGaussian::function ( const double  lambda_ ) const

virtual

Parameters

[in]

lambda_

Eigenvalue (or singular value) of matrix.

Returns

The value of matrix function for the given eigenvalue.

Implements Function.

Definition at line 66 of file log_gaussian.cpp.

{
    double x = (std::log(lambda_) - std::log(this->mu)) / this->sigma;
    return (0.5 * M_SQRT1_2 * M_2_SQRTPI / this->sigma) * \
        std::exp(-0.5 * x * x) / lambda_;
}

References mu, and sigma.

function() [2/3]

float LogGaussian::function ( const float  lambda_ ) const

virtual

Parameters

[in]

lambda_

Eigenvalue (or singular value) of matrix.

Returns

The value of matrix function for the given eigenvalue.

Implements Function.

Definition at line 48 of file log_gaussian.cpp.

{
    float mu_ = static_cast<float>(this->mu);
    float sigma_ = static_cast<float>(this->sigma);
    float x = (std::log(lambda_) - std::log(mu_)) / sigma_;
    return (0.5f * M_SQRT1_2 * M_2_SQRTPI / sigma_) * \
        std::exp(-0.5f * x * x) / lambda_;
}

References mu, and sigma.

function() [3/3]

long double LogGaussian::function ( const long double  lambda_ ) const

virtual

Parameters

[in]

lambda_

Eigenvalue (or singular value) of matrix.

Returns

The value of matrix function for the given eigenvalue.

Implements Function.

Definition at line 82 of file log_gaussian.cpp.

{
    long double mu_ = static_cast<long double>(this->mu);
    long double sigma_ = static_cast<long double>(this->sigma);
    long double x = (std::log(lambda_) - std::log(mu_)) / sigma_;
    return (0.5l * M_SQRT1_2 * M_2_SQRTPI / sigma_) * \
        std::exp(-0.5l * x * x) / lambda_;
}

References mu, and sigma.

Member Data Documentation

mu

double LogGaussian::mu

Definition at line 58 of file log_gaussian.h.

Referenced by function(), function(), function(), and LogGaussian().

sigma

double LogGaussian::sigma

Definition at line 59 of file log_gaussian.h.

Referenced by function(), function(), function(), and LogGaussian().

---

The documentation for this class was generated from the following files:

• /home/runner/work/imate/imate/imate/functions/log_gaussian.h
• /home/runner/work/imate/imate/imate/functions/log_gaussian.cpp