#include <types.hpp>
Inheritance diagram for sspace::qlognormal:
Public Member Functions | |
| qlognormal (std::string n, double mu, double sigma, double q) | |
| double | sample () |
 Public Member Functions inherited from sspace::lognormal | |
| lognormal (std::string n, double mu, double sigma) | |
| lognormal (std::string n, double mu, double sigma, pt t) | |
| Public Member Functions inherited from sspace::normal | |
| normal (std::string n, double mu, double sigma) | |
| normal (std::string n, double mu, double sigma, pt t) | |
| Public Member Functions inherited from sspace::param_t | |
| param_t (std::string n, pt t) | |
| virtual | ~param_t () |
| virtual pt | get_type () |
| virtual std::string | get_name () |
Public Attributes | |
| double | m_q |
| Public Attributes inherited from sspace::normal | |
| double | m_mu |
| double | m_sigma |
Additional Inherited Members | |
| Protected Attributes inherited from sspace::normal | |
| std::random_device | rd |
| std::mt19937 | generator |
| std::normal_distribution< double > | dist |
Detailed Description
qlognormal is a quantised parameter which follows a log-normal distribution.
This is suitable for discrete-valued variables with respect to which the objective function becomes smoother as the size of the variable, which is bounded to one size, increases.
Constructor & Destructor Documentation
◆ qlognormal()
| sspace::qlognormal::qlognormal | ( | std::string | n, |
| double | mu, | ||
| double | sigma, | ||
| double | q | ||
| ) |
The constructor
- Parameters
-
n The name of this parameter mu The mean of the normal distribution sigma The standard deviation of the normal distribution q The quantisation to apply to the output
Member Function Documentation
◆ sample()
|
virtual |
Samples values from a quantised exponential normal distribution according to the formula:
\[ v = \text{round}\bigg(\text{lognormal}(\mu, \sigma) / q\bigg)\cdot q. \]
Reimplemented from sspace::lognormal.
The documentation for this class was generated from the following files:
