Purple::RandomSearch Class Reference

Inheritance diagram for Purple::RandomSearch:

List of all members.

Public Member Functions
	RandomSearch (ObjectiveFunction *)
	RandomSearch (void)
virtual	~RandomSearch (void)
int	getMaximumNumberOfIterations (void)
int	getShowPeriod (void)
void	setMaximumNumberOfIterations (int)
void	setShowPeriod (int)
Vector< double >	getMinimalArgument (void)
void	print (void)
void	load (char *)
void	save (char *)
void	saveOptimizationHistory (char *)
Private Attributes
Vector< double >	evaluationHistory
int	maximumNumberOfIterations
int	showPeriod

---

Detailed Description

This concrete class represents the random search optimization algorithm.

See also:

ObjectiveFunction.

OptimizationAlgorithm.

Definition at line 27 of file RandomSearch.h.

---

Constructor & Destructor Documentation

Purple::RandomSearch::RandomSearch

(

ObjectiveFunction *

newObjectiveFunction

)

General constructor. It creates a random search optimization algorithm object associated to an objective function object. It also initializes the class members to their default values:

Stopping criteria:

• Evaluation goal: -1.0e69.
• Maximum time: 1.0e6.
• Maximum number of iterations: 100.

User stuff:

• Show period: 10.

Parameters:

newObjectiveFunction,:

Pointer to an objective function object.

Definition at line 46 of file RandomSearch.cpp.

Purple::RandomSearch::RandomSearch

(

void

)

Default constructor. It creates a random search optimization algorithm object not associated to any objective function object. It also initializes the class members to their default values:

Stopping criteria:

• Evaluation goal: -1.0e69.
• Maximum time: 1.0e6.
• Maximum number of evaluations: 100.

User stuff:

• Show period: 10.

Definition at line 79 of file RandomSearch.cpp.

Purple::RandomSearch::~RandomSearch

(

void

)

[virtual]

Destructor.

Definition at line 97 of file RandomSearch.cpp.

---

Member Function Documentation

int Purple::RandomSearch::getMaximumNumberOfIterations

(

void

)

This method returns the maximum number of iterations in the optimization process.

Definition at line 109 of file RandomSearch.cpp.

int Purple::RandomSearch::getShowPeriod

(

void

)

This method returns the number of iterations between the optimization showing progress.

Definition at line 120 of file RandomSearch.cpp.

void Purple::RandomSearch::setMaximumNumberOfIterations

(

int

newMaximumNumberOfIterations

)

This method sets a maximum number of iterations for optimization. Each iteration with the random search optimization algorithms costs one objective function evaluation.

Parameters:

newMaximumNumberOfIterations,:

Maximum number of iterations for optimization.

Definition at line 136 of file RandomSearch.cpp.

void Purple::RandomSearch::setShowPeriod

(

int

newShowPeriod

)

This method sets a new number of iterations between the optimization showing progress.

Parameters:

newShowPeriod,:

Show period.

Definition at line 164 of file RandomSearch.cpp.

Vector< double > Purple::RandomSearch::getMinimalArgument

(

void

)

[virtual]

This method returns the miminal argument of the associated objective function according to the random search optimization algorithm. Optimization occurs according to the optimization parameters.

Implements Purple::OptimizationAlgorithm.

Definition at line 190 of file RandomSearch.cpp.

void Purple::RandomSearch::print

(

void

)

This method prints to the screen the optimization parameters concerning the random search object:

Stopping criteria:

• Evaluation goal.
• Gradient norm goal.
• Maximum time.
• Maximum number of iterations.

User stuff:

• Show period.

Definition at line 389 of file RandomSearch.cpp.

void Purple::RandomSearch::load

(

char *

filename

)

This method loads a random search object from a data file. Please mind about the file format, wich is specified in the User's Guide.

Stopping criteria:

• Evaluation goal.
• Maximum time.
• Maximum number of evaluations.

User stuff:

• Evaluations between showing progress.

Parameters:

filename,:

Filename.

See also:

save(char*).

Definition at line 508 of file RandomSearch.cpp.

void Purple::RandomSearch::save

(

char *

filename

)

This method saves the random search object to a data file.

Stopping criteria:

• Evaluation goal.
• Maximum time.
• Maximum number of evaluations.

User stuff:

• Evaluations between showing progress.

Parameters:

filename,:

Filename.

See also:

load(char*).

Definition at line 436 of file RandomSearch.cpp.

void Purple::RandomSearch::saveOptimizationHistory

(

char *

filename

)

This method saves the optimization history to a data file.

1. Iteration.
2. Objective function evaluation.

Parameters:

filename,:

Filename.

Definition at line 582 of file RandomSearch.cpp.

---

Member Data Documentation

Vector<double> Purple::RandomSearch::evaluationHistory [private]

Objective function evaluation history.

Definition at line 36 of file RandomSearch.h.

int Purple::RandomSearch::maximumNumberOfIterations [private]

Maximum number of iterations. It is used as a train stopping criterion.

Definition at line 41 of file RandomSearch.h.

int Purple::RandomSearch::showPeriod [private]

Number of iterations between the training showing progress.

Definition at line 45 of file RandomSearch.h.

---