Generic class for Evolution Strategy parameters. More...

#include <libcmaes/parameters.h>

Inheritance diagram for libcmaes::Parameters< TGenoPheno >:

Public Member Functions
	Parameters ()
	empty constructor.

	Parameters (const int &dim, const double *x0, const int &lambda=-1, const uint64_t &seed=0, const TGenoPheno &gp=GenoPheno< NoBoundStrategy >())
	constructor

void	set_x0 (const double &x0)
	sets initial objective function parameter values to x0 across all dimensions

void	set_x0 (const double *x0)
	sets initial objective function parameter values to array x0

void	set_x0 (const dVec &x0)
	sets initial objective function parameter values from Eigen vector

void	set_x0 (const double &x0min, const double &x0max)
	sets bounds on initial objective function parameter values. Bounds are the same across all dimensions, and initial value is sampled uniformly within these bounds.

void	set_x0 (const double x0min, const double x0max)
	sets bounds on initial objective function parameter values. Initial value is sampled uniformly within these bounds.

void	set_x0 (const std::vector< double > &x0min, const std::vector< double > &x0max)
	sets bounds on initial objective function parameter values. Initial value is sampled uniformly within these bounds.

void	set_x0 (const dVec &x0min, const dVec &x0max)
	sets bounds on initial objective function parameter values. Initial value is sampled uniformly within these bounds.

dVec	get_x0min () const
	returns lower bound on x0 vector

dVec	get_x0max () const
	returns upper bound on x0 vector

void	set_fixed_p (const int &index, const double &value)
	freezes a parameter to a given value during optimization.

void	unset_fixed_p (const int &index)
	unfreezes a parameter.

void	set_max_iter (const int &maxiter)
	sets the maximum number of iterations allowed for the optimization.

int	get_max_iter () const
	returns maximum number of iterations

void	set_max_fevals (const int &fevals)
	sets the maximum budget of objective function calls allowed for the optimization.

int	get_max_fevals () const
	returns maximum budget of objective function calls

void	set_ftarget (const double &val)
	sets the objective function target value when known.

void	reset_ftarget ()
	resets the objective function target value to its inactive state.

double	get_ftarget () const
	returns objective function target value.

void	set_seed (const int &seed)
	sets random generator's seed, 0 is special value to generate random seed.

int	get_seed () const
	returns random generator's seed.

void	set_ftolerance (const double &v)
	sets function tolerance as stopping criteria for TolHistFun: monitors the difference in function value over iterations and stops optimization when below tolerance.

double	get_ftolerance () const
	returns function tolerance

void	set_xtolerance (const double &v)
	sets parameter tolerance as stopping criteria for TolX.

double	get_xtolerance () const
	returns parameter tolerance

int	lambda () const
	returns lambda, number of offsprings per generation

int	dim () const
	returns the problem's dimension

void	set_quiet (const bool &quiet)
	sets the quiet mode (no output from the library) for the optimization at hand

bool	quiet () const
	returns whether the quiet mode is on.

void	set_algo (const int &algo)
	sets the optimization algorithm.

int	get_algo () const
	returns which algorithm is set for the optimization at hand.

void	set_gp (const TGenoPheno &gp)
	sets the genotype/phenotype transform object.

TGenoPheno	get_gp () const
	returns the current genotype/phenotype transform object.

void	set_fplot (const std::string &fplot)
	sets the output filename (activates the output to file).

void	set_full_fplot (const bool &b)
	activates / deactivates the full output (for legacy plotting).

std::string	get_fplot () const
	returns the current output filename.

void	set_gradient (const bool &gradient)
	activates the gradient injection scheme. If no gradient function is defined, injects a numerical gradient solution instead

bool	get_gradient () const
	returns whether the gradient injection scheme is activated.

void	set_edm (const bool &edm)
	activates computation of expected distance to minimum when optimization has completed

bool	get_edm () const
	returns whether edm is activated.

void	set_mt_feval (const bool &mt)
	activate / deactivate the parallel evaluation of objective function

bool	get_mt_feval () const
	returns whether the parallel evaluation of objective function is activated

void	set_max_hist (const int &m)
	sets maximum history size, allows to keep memory requirements fixed.

void	set_maximize (const bool &maximize)
	active internal maximization scheme (simply returns -f instead of f)

bool	get_maximize () const
	returns whether the maximization mode is enabled

void	set_initial_fvalue (const bool &b)
	whether to compute initial objective function value (i.e. at x0)

void	set_uh (const bool &b)
	activates / deactivates uncertainty handling scheme.

bool	get_uh () const
	get uncertainty handling status.

void	set_tpa (const int &b)
	activates / deactivates two-point adaptation step-size mechanism

int	get_tpa () const
	get two-point adapation step-size mechanism status.

Protected Attributes
int	_dim

int	_lambda = -1

int	_max_iter = -1

int	_max_fevals = -1

bool	_quiet = true

std::string	_fplot = ""

bool	_full_fplot = false

dVec	_x0min

dVec	_x0max

double	_ftarget = -std::numeric_limits<double>::infinity()

double	_ftolerance = 1e-12

double	_xtol = 1e-12

uint64_t	_seed = 0

int	_algo = 0

bool	_with_gradient =false

bool	_with_edm =false

std::unordered_map< int, double >	_fixed_p

TGenoPheno	_gp

bool	_mt_feval = false

int	_max_hist = -1

bool	_maximize = false

bool	_initial_fvalue = false

bool	_uh = false

double	_rlambda

double	_epsuh = 1e-7

double	_thetauh = 0.2

double	_csuh = 1.0

double	_alphathuh = 1.0

int	_tpa = 1

double	_tpa_csigma = 0.3

Static Protected Attributes
static std::map< std::string, int >	_algos = {{"cmaes",0},{"ipop",1},{"bipop",2},{"acmaes",3},{"aipop",4},{"abipop",5},{"sepcmaes",6},{"sepipop",7},{"sepbipop",8},{"sepacmaes",9},{"sepaipop",10},{"sepabipop",11},{"vdcma",12},{"vdipopcma",13},{"vdbipopcma",14}}

Friends
class	CMASolutions

template<class U , class V >
class	CMAStrategy

template<class U , class V , class W >
class	ESOStrategy

template<class U >
class	CMAStopCriteria

template<class U , class V >
class	IPOPCMAStrategy

template<class U , class V >
class	BIPOPCMAStrategy

class	CovarianceUpdate

class	ACovarianceUpdate

template<class U >
class	errstats

class	VDCMAUpdate

class	Candidate

Detailed Description

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>
class libcmaes::Parameters< TGenoPheno >

Generic class for Evolution Strategy parameters.

Constructor & Destructor Documentation

◆ Parameters()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

libcmaes::Parameters< TGenoPheno >::Parameters	(	const int &	dim,
		const double *	x0,
		const int &	lambda = `-1`,
		const uint64_t &	seed = `0`,
		const TGenoPheno &	gp = `GenoPheno<NoBoundStrategy>()`
	)

inline

constructor

Parameters

dim	problem dimensions
x0	initial search point
lambda	number of offsprings sampled at each step
seed	initial random seed, useful for reproducing results (if unspecified, automatically generated from current time)
gp	genotype / phenotype object

Member Function Documentation

◆ dim()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

int libcmaes::Parameters< TGenoPheno >::dim ( ) const

inline

returns the problem's dimension

Returns: dimensions

◆ get_algo()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

int libcmaes::Parameters< TGenoPheno >::get_algo ( ) const

inline

returns which algorithm is set for the optimization at hand.

Returns: algorithm integer code

◆ get_edm()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

bool libcmaes::Parameters< TGenoPheno >::get_edm ( ) const

inline

returns whether edm is activated.

Returns: edm

◆ get_fplot()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

std::string libcmaes::Parameters< TGenoPheno >::get_fplot ( ) const

inline

returns the current output filename.

Returns: output filename

◆ get_ftarget()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

double libcmaes::Parameters< TGenoPheno >::get_ftarget ( ) const

inline

returns objective function target value.

Returns: objective function target value

◆ get_ftolerance()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

double libcmaes::Parameters< TGenoPheno >::get_ftolerance ( ) const

inline

returns function tolerance

Returns: function tolerance

◆ get_gp()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

TGenoPheno libcmaes::Parameters< TGenoPheno >::get_gp ( ) const

inline

returns the current genotype/phenotype transform object.

Returns: GenoPheno object

◆ get_gradient()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

bool libcmaes::Parameters< TGenoPheno >::get_gradient ( ) const

inline

returns whether the gradient injection scheme is activated.

Returns: with gradient

◆ get_max_fevals()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

int libcmaes::Parameters< TGenoPheno >::get_max_fevals ( ) const

inline

returns maximum budget of objective function calls

Returns: max number of objective function evaluations

◆ get_max_iter()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

int libcmaes::Parameters< TGenoPheno >::get_max_iter ( ) const

inline

returns maximum number of iterations

Returns: max number of iterations allowed

◆ get_maximize()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

bool libcmaes::Parameters< TGenoPheno >::get_maximize ( ) const

inline

returns whether the maximization mode is enabled

Returns: true if maximizing

◆ get_mt_feval()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

bool libcmaes::Parameters< TGenoPheno >::get_mt_feval ( ) const

inline

returns whether the parallel evaluation of objective function is activated

Returns: activation status

◆ get_seed()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

int libcmaes::Parameters< TGenoPheno >::get_seed ( ) const

inline

returns random generator's seed.

Returns: integer seed

◆ get_tpa()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

int libcmaes::Parameters< TGenoPheno >::get_tpa ( ) const

inline

get two-point adapation step-size mechanism status.

Returns: two-point adaptation status.

◆ get_uh()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

bool libcmaes::Parameters< TGenoPheno >::get_uh ( ) const

inline

get uncertainty handling status.

Returns: uncertainty handling status.

◆ get_x0max()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

dVec libcmaes::Parameters< TGenoPheno >::get_x0max ( ) const

inline

returns upper bound on x0 vector

Returns: upper bound on x0

◆ get_x0min()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

dVec libcmaes::Parameters< TGenoPheno >::get_x0min ( ) const

inline

returns lower bound on x0 vector

Returns: lower bound on x0

◆ get_xtolerance()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

double libcmaes::Parameters< TGenoPheno >::get_xtolerance ( ) const

inline

returns parameter tolerance

Returns: parameter tolerance

◆ lambda()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

int libcmaes::Parameters< TGenoPheno >::lambda ( ) const

inline

returns lambda, number of offsprings per generation

Returns: lambda

◆ quiet()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

bool libcmaes::Parameters< TGenoPheno >::quiet ( ) const

inline

returns whether the quiet mode is on.

Returns: quiet mode

◆ set_algo()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_algo ( const int & algo )

inline

sets the optimization algorithm.

Parameters

algo	from CMAES_DEFAULT, IPOP_CMAES, BIPOP_CMAES, aCMAES, aIPOP_CMAES, aBIPOP_CMAES, sepCMAES, sepIPOP_CMAES, sepBIPOP_CMAES, sepaCMAES, sepaIPOP_CMAES, sepaBIPOP_CMAES, VD_CMAES, VD_IPOP_CMAES, VD_BIPOP_CMAES

◆ set_edm()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_edm ( const bool & edm )

inline

activates computation of expected distance to minimum when optimization has completed

Parameters

edm	true / false

◆ set_fixed_p()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_fixed_p	(	const int &	index,
		const double &	value
	)

inline

freezes a parameter to a given value during optimization.

Parameters

index	dimension index of the parameter to be frozen
value	frozen value of the parameter

◆ set_fplot()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_fplot ( const std::string & fplot )

inline

sets the output filename (activates the output to file).

Parameters

fplot filename

◆ set_ftarget()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_ftarget ( const double & val )

inline

sets the objective function target value when known.

Parameters

val	objective function target value

◆ set_ftolerance()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_ftolerance ( const double & v )

inline

sets function tolerance as stopping criteria for TolHistFun: monitors the difference in function value over iterations and stops optimization when below tolerance.

Parameters

v	value of the function tolerance.

◆ set_full_fplot()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_full_fplot ( const bool & b )

inline

activates / deactivates the full output (for legacy plotting).

Parameters

b	whether to activate / deactivate

◆ set_gp()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_gp ( const TGenoPheno & gp )

inline

sets the genotype/phenotype transform object.

Parameters

gp	GenoPheno object

◆ set_gradient()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_gradient ( const bool & gradient )

inline

activates the gradient injection scheme. If no gradient function is defined, injects a numerical gradient solution instead

Parameters

gradient true/false

◆ set_initial_fvalue()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_initial_fvalue ( const bool & b )

inline

whether to compute initial objective function value (i.e. at x0)

Parameters

b	activates / deactivates

◆ set_max_fevals()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_max_fevals ( const int & fevals )

inline

sets the maximum budget of objective function calls allowed for the optimization.

Parameters

fevals maximum number of objective function evaluations

◆ set_max_hist()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_max_hist ( const int & m )

inline

sets maximum history size, allows to keep memory requirements fixed.

Parameters

m	number of steps of candidate history that are kept into memory (for stopping criteria equalfunvals mostly).

◆ set_max_iter()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_max_iter ( const int & maxiter )

inline

sets the maximum number of iterations allowed for the optimization.

Parameters

maxiter maximum number of allowed iterations

◆ set_maximize()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_maximize ( const bool & maximize )

inline

active internal maximization scheme (simply returns -f instead of f)

Parameters

maximize whether to maximize instead of minimizing

◆ set_mt_feval()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_mt_feval ( const bool & mt )

inline

activate / deactivate the parallel evaluation of objective function

Parameters

mt	true for activated, false otherwise

◆ set_quiet()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_quiet ( const bool & quiet )

inline

sets the quiet mode (no output from the library) for the optimization at hand

Parameters

quiet true / false

◆ set_seed()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_seed ( const int & seed )

inline

sets random generator's seed, 0 is special value to generate random seed.

Parameters

seed	integer seed

◆ set_tpa()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_tpa ( const int & b )

inline

activates / deactivates two-point adaptation step-size mechanism

Parameters

b	0: no, 1: auto, 2: yes

◆ set_uh()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_uh ( const bool & b )

inline

activates / deactivates uncertainty handling scheme.

Parameters

b	activates / deactivates

◆ set_x0() [1/7]

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_x0 ( const double & x0 )

inline

sets initial objective function parameter values to x0 across all dimensions

Parameters

x0	initial value

◆ set_x0() [2/7]

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_x0	(	const double &	x0min,
		const double &	x0max
	)

inline

sets bounds on initial objective function parameter values. Bounds are the same across all dimensions, and initial value is sampled uniformly within these bounds.

Parameters

x0min	lower bound
x0max	upper bound

◆ set_x0() [3/7]

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_x0 ( const double * x0 )

inline

sets initial objective function parameter values to array x0

Parameters

x0	array of initial parameter values

◆ set_x0() [4/7]

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_x0	(	const double *	x0min,
		const double *	x0max
	)

inline

sets bounds on initial objective function parameter values. Initial value is sampled uniformly within these bounds.

Parameters

x0min	vector of initial lower bounds.
x0max	vector of initial upper bounds.

◆ set_x0() [5/7]

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_x0 ( const dVec & x0 )

inline

sets initial objective function parameter values from Eigen vector

Parameters

x0	Eigen vector of initial parameter values

◆ set_x0() [6/7]

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_x0	(	const dVec &	x0min,
		const dVec &	x0max
	)

inline

sets bounds on initial objective function parameter values. Initial value is sampled uniformly within these bounds.

Parameters

x0min	vector of initial lower bounds.
x0max	vector of initial upper bounds.

◆ set_x0() [7/7]

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_x0	(	const std::vector< double > &	x0min,
		const std::vector< double > &	x0max
	)

inline

sets bounds on initial objective function parameter values. Initial value is sampled uniformly within these bounds.

Parameters

x0min	vector of initial lower bounds.
x0max	vector of initial upper bounds.

◆ set_xtolerance()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::set_xtolerance ( const double & v )

inline

sets parameter tolerance as stopping criteria for TolX.

Parameters

v	value of the parameter tolerance.

◆ unset_fixed_p()

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

void libcmaes::Parameters< TGenoPheno >::unset_fixed_p ( const int & index )

inline

unfreezes a parameter.

Parameters

index dimenion index of the parameter to unfreeze

Member Data Documentation

◆ _algo

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

int libcmaes::Parameters< TGenoPheno >::_algo = 0

protected

selected algorithm.

◆ _algos

template<class TGenoPheno >

std::map< std::string, int > libcmaes::Parameters< TGenoPheno >::_algos = {{"cmaes",0},{"ipop",1},{"bipop",2},{"acmaes",3},{"aipop",4},{"abipop",5},{"sepcmaes",6},{"sepipop",7},{"sepbipop",8},{"sepacmaes",9},{"sepaipop",10},{"sepabipop",11},{"vdcma",12},{"vdipopcma",13},{"vdbipopcma",14}}

staticprotected

of the form { {"cmaes",0}, {"ipop",1}, ...}

◆ _alphathuh

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

double libcmaes::Parameters< TGenoPheno >::_alphathuh = 1.0

protected

factor of increasing the population spread.

◆ _csuh

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

double libcmaes::Parameters< TGenoPheno >::_csuh = 1.0

protected

learning rate for averaging the uncertainty measurement.

◆ _dim

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

int libcmaes::Parameters< TGenoPheno >::_dim

protected

function space dimensions.

◆ _epsuh

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

double libcmaes::Parameters< TGenoPheno >::_epsuh = 1e-7

protected

mutation strength for the reevaluation.

◆ _fixed_p

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

std::unordered_map<int,double> libcmaes::Parameters< TGenoPheno >::_fixed_p

protected

fixed parameters and values.

◆ _fplot

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

std::string libcmaes::Parameters< TGenoPheno >::_fplot = ""

protected

plotting file, if specified.

◆ _ftarget

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

double libcmaes::Parameters< TGenoPheno >::_ftarget = -std::numeric_limits<double>::infinity()

protected

optional objective function target value.

◆ _ftolerance

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

double libcmaes::Parameters< TGenoPheno >::_ftolerance = 1e-12

protected

tolerance of the best function values during the last 10+(30*dim/lambda) steps (TolHistFun).

◆ _full_fplot

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

bool libcmaes::Parameters< TGenoPheno >::_full_fplot = false

protected

whether to write to file full legacy data output.

◆ _gp

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

TGenoPheno libcmaes::Parameters< TGenoPheno >::_gp

protected

genotype / phenotype object.

◆ _initial_fvalue

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

bool libcmaes::Parameters< TGenoPheno >::_initial_fvalue = false

protected

whether to compute initial objective function value (not required).

◆ _lambda

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

int libcmaes::Parameters< TGenoPheno >::_lambda = -1

protected

number of offsprings.

◆ _max_fevals

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

int libcmaes::Parameters< TGenoPheno >::_max_fevals = -1

protected

max budget as number of function evaluations.

◆ _max_hist

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

int libcmaes::Parameters< TGenoPheno >::_max_hist = -1

protected

max size of the history, keeps memory requirements fixed.

◆ _max_iter

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

int libcmaes::Parameters< TGenoPheno >::_max_iter = -1

protected

max iterations.

◆ _maximize

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

bool libcmaes::Parameters< TGenoPheno >::_maximize = false

protected

convenience option of maximizing -f instead of minimizing f.

◆ _mt_feval

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

bool libcmaes::Parameters< TGenoPheno >::_mt_feval = false

protected

whether to force multithreaded (i.e. parallel) function evaluations.

◆ _quiet

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

bool libcmaes::Parameters< TGenoPheno >::_quiet = true

protected

quiet all outputs.

◆ _rlambda

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

double libcmaes::Parameters< TGenoPheno >::_rlambda

protected

fraction of solutions to be reevaluated.

◆ _seed

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

uint64_t libcmaes::Parameters< TGenoPheno >::_seed = 0

protected

seed for random generator.

◆ _thetauh

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

double libcmaes::Parameters< TGenoPheno >::_thetauh = 0.2

protected

control parameter for the acceptance threshold for the measured rank-change value.

◆ _tpa

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

int libcmaes::Parameters< TGenoPheno >::_tpa = 1

protected

whether to activate two-point adaptation, 0: no (forced), 1: auto, 2: yes (forced)

◆ _uh

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

bool libcmaes::Parameters< TGenoPheno >::_uh = false

protected

whether to activate uncertainty handling.

◆ _with_edm

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

bool libcmaes::Parameters< TGenoPheno >::_with_edm =false

protected

whether to compute expected distance to minimum when optimization has completed.

◆ _with_gradient

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

bool libcmaes::Parameters< TGenoPheno >::_with_gradient =false

protected

whether to use injected gradient.

◆ _x0max

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

dVec libcmaes::Parameters< TGenoPheno >::_x0max

protected

initial mean vector max bound value for all components.

◆ _x0min

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

dVec libcmaes::Parameters< TGenoPheno >::_x0min

protected

initial mean vector min bound value for all components.

◆ _xtol

template<class TGenoPheno = GenoPheno<NoBoundStrategy>>

double libcmaes::Parameters< TGenoPheno >::_xtol = 1e-12

protected

tolerance on parameters error.

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

include/libcmaes/parameters.h
include/libcmaes/cmaparameters.h

Public Member Functions

Protected Attributes

Static Protected Attributes

Friends

Detailed Description

Constructor & Destructor Documentation

◆ Parameters()

Member Function Documentation

◆ dim()

◆ get_algo()

◆ get_edm()

◆ get_fplot()

◆ get_ftarget()

◆ get_ftolerance()

◆ get_gp()

◆ get_gradient()

◆ get_max_fevals()

◆ get_max_iter()

◆ get_maximize()

◆ get_mt_feval()

◆ get_seed()

◆ get_tpa()

◆ get_uh()

◆ get_x0max()

◆ get_x0min()

◆ get_xtolerance()

◆ lambda()

◆ quiet()

◆ set_algo()

◆ set_edm()

◆ set_fixed_p()

◆ set_fplot()

◆ set_ftarget()

◆ set_ftolerance()

◆ set_full_fplot()

◆ set_gp()

◆ set_gradient()

◆ set_initial_fvalue()

◆ set_max_fevals()

◆ set_max_hist()

◆ set_max_iter()

◆ set_maximize()

◆ set_mt_feval()

◆ set_quiet()

◆ set_seed()

◆ set_tpa()

◆ set_uh()

◆ set_x0() [1/7]

◆ set_x0() [2/7]

◆ set_x0() [3/7]

◆ set_x0() [4/7]

◆ set_x0() [5/7]

◆ set_x0() [6/7]

◆ set_x0() [7/7]

◆ set_xtolerance()

◆ unset_fixed_p()

Member Data Documentation

◆ _algo

◆ _algos

◆ _alphathuh

◆ _csuh

◆ _dim

◆ _epsuh

◆ _fixed_p

◆ _fplot

◆ _ftarget

◆ _ftolerance

◆ _full_fplot

◆ _gp

◆ _initial_fvalue

◆ _lambda

◆ _max_fevals

◆ _max_hist

◆ _max_iter

◆ _maximize

◆ _mt_feval

◆ _quiet

◆ _rlambda

◆ _seed

◆ _thetauh