Documentation
¶
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Engine ¶
type Engine struct {
// contains filtered or unexported fields
}
Engine is Sobol's quasirandom number generator.
type Sampler ¶
type Sampler struct {
// contains filtered or unexported fields
}
Sampler for quasi-Monte Carlo Sampling based on Sobol sequence. It is recommended to use "SamplerOptionSkipInitialPoints(n)" for better performance. Furthermore, if you use this sampler from multiple workers, you need to specify different "n" argument for each workers to remove duplicated parameters.
type SamplerOption ¶
type SamplerOption func(sampler *Sampler)
SamplerOption is a type of function to set options.
func SamplerOptionSkipInitialPoints ¶
func SamplerOptionSkipInitialPoints(nSamples uint32) SamplerOption
SamplerOptionSkipInitialPoints to skip the number of initial points. Joe&Kuo recommended to drop initial portion of sequence. Thereby, Sobol' sequence tends to perform better. This function takes 'nSamples' argument which is the number of points to be used (= the number of objective function calls), then skips the largest power of 2 points smaller than nSample.