Namespace of the library interface. More...

Namespaces
	utils
	Extra utils: math functions, ublas helpers, etc.

Classes
class	AnnealedExpectedImprovement
	Expected improvement criterion using Schonlau annealing. [Schonlau98]. More...

class	AnnealedLowerConfindenceBound
	Lower (upper) confidence bound using Srinivas annealing [Srinivas10]. More...

class	ARDkernel
	Abstract class for anisotropic kernel functors using ARD (Automatic Relevance Determination) More...

class	AtomicFunction
	Abstract class for an atomic kernel. More...

class	AtomicKernel
	Abstract class for an atomic kernel. More...

class	BayesOptBase
	Abstract module for Bayesian optimization. More...

class	BiasedExpectedImprovement
	Expected improvement criterion modification by Lizotte. More...

class	BOptState
	Class that represents the state of an optimization. More...

class	CombinedCriteria
	Abstract class for combined criteria functions. More...

class	CombinedFunction
	Abstract class for combined functions. More...

class	CombinedKernel
	Abstract class for combined kernel. More...

class	ConditionalBayesProcess
	Empirical Bayesian NonParametric process. More...

class	ConstantFunction
	Constant function. More...

class	ConstKernel
	Constant kernel. More...

class	ContinuousModel
	Bayesian optimization for functions in continuous input spaces. More...

class	CritCallback

class	Criteria
	Abstract interface for criteria functors. More...

class	CriteriaFactory
	Factory model for criterion functions This factory is based on the libgp library by Manuel Blum https://bitbucket.org/mblum/libgp which follows the squeme of GPML by Rasmussen and Nickisch http://www.gaussianprocess.org/gpml/code/matlab/doc/. More...

class	Dataset
	Dataset model to deal with the vector (real) based datasets. More...

class	DiscreteModel
	Bayesian optimization for functions in discrete spaces. More...

class	EmpiricalBayes
	Bayesian optimization using different non-parametric processes as distributions over surrogate functions. More...

class	ExpectedImprovement
	Expected improvement criterion by Mockus [Mockus78]. More...

class	ExpectedReturn
	Expected return criterion. More...

class	GaussianDistribution

class	GaussianProcess
	Standard zero mean gaussian process with noisy observations. More...

class	GaussianProcessML
	Gaussian process with ML parameters. More...

class	GaussianProcessNormal
	Gaussian process with normal prior on the parameters. More...

class	GP_Hedge
	GP_Hedge model as describen in Hoffman et al. More...

class	GP_Hedge_Random
	Modification of the GP_Hedge algorithm where the bandit gains are random outcomes (like Thompson sampling). More...

class	GreedyAOptimality
	Greedy A-Optimality criterion. More...

class	HammingKernel
	Kernel for categorical data. More...

class	HierarchicalGaussianProcess
	Virtual class for hierarchical Gaussian processes. More...

class	InputDistance
	Distance in input space. More...

class	ISOkernel
	Abstract class for isotropic kernel functors. More...

class	Kernel
	Interface for kernel functors. More...

class	KernelFactory
	Factory model for kernel functions This factory is based on the libgp library by Manuel Blum https://bitbucket.org/mblum/libgp which follows the squeme of GPML by Rasmussen and Nickisch http://www.gaussianprocess.org/gpml/code/matlab/doc/. More...

class	KernelModel

class	KernelParameters

class	KernelProd
	Product of two kernels. More...

class	KernelRegressor
	Abstract class to implement non-parametric processes. More...

class	KernelSum
	Sum of two kernels. More...

class	LinearFunction
	Linear combination function. More...

class	LinearPlusConstantFunction
	Linear combination plus constant function. More...

class	LinKernel
	Linear kernel. More...

class	LinKernelARD
	Linear kernel. More...

class	LowerConfidenceBound
	Lower (upper) confidence bound criterion by [Cox and John, 1992]. More...

class	MaternARD1
	Matern ARD kernel of 1st order. More...

class	MaternARD3
	Matern ARD kernel of 3rd order. More...

class	MaternARD5
	Matern ARD kernel of 5th order. More...

class	MaternIso1
	Matern isotropic kernel of 1st order. More...

class	MaternIso3
	Matern kernel of 3rd order. More...

class	MaternIso5
	Matern isotropic kernel of 5th order. More...

class	MCMCModel
	Posterior model of nonparametric processes/criteria based on MCMC samples. More...

class	MCMCSampler
	Markov Chain Monte Carlo sampler. More...

class	MeanFactory
	Factory model for parametric functions This factory is based on the libgp library by Manuel Blum https://bitbucket.org/mblum/libgp which follows the squeme of GPML by Rasmussen and Nickisch http://www.gaussianprocess.org/gpml/code/matlab/doc/. More...

class	MeanModel

class	MeanParameters

class	MutualInformation
	Mutual Information bound criterion b [Contal et al., 2014]. More...

class	NLOPT_Optimization

class	NonParametricProcess
	Abstract class to implement Bayesian regressors. More...

class	OneFunction
	Constant one function. More...

class	OptimisticSampling
	Optimistic sampling. More...

class	Parameters

class	ParametricFunction
	Interface for mean functors. More...

class	Polynomial
	Polynomial covariance function. More...

class	Polynomial2

class	Polynomial3

class	Polynomial4

class	Polynomial5

class	Polynomial6

class	Polynomial7

class	PosteriorFixed
	Bayesian optimization using different non-parametric processes as distributions over surrogate functions. More...

class	PosteriorModel
	Bayesian optimization using different non-parametric processes as distributions over surrogate functions. More...

class	ProbabilityDistribution

class	ProbabilityOfImprovement
	Probability of improvement criterion based on (Kushner). More...

class	ProdCriteria
	Product of criterion functions. More...

class	RBOptimizable

class	RBOptimizableWrapper

class	RGBOptimizable

class	RGBOptimizableWrapper

class	RQIso
	Rational quadratic (Student's t) kernel. More...

class	SEArd
	Square exponential (Gaussian) kernel. More...

class	SEIso
	Square exponential (Gaussian) kernel. More...

class	StudentTDistribution

class	StudentTProcessJeffreys
	Student T process with Jeffreys prior. More...

class	StudentTProcessNIG
	Student's t process with Normal Inverse-Gamma hyperprior on mean and snigal variance parameters. More...

class	SumCriteria
	Wrapper class for linear combination of criterion functions. More...

class	SumFunction
	Sum of two kernels. More...

class	ThompsonSampling
	Thompson sampling. Picks a random sample of the surrogate model. More...

class	ZeroFunction
	Constant zero function. More...

Typedefs
typedef boost::numeric::ublas::vector< double >	vectord

typedef boost::numeric::ublas::vector< int >	vectori

typedef boost::numeric::ublas::matrix< double >	matrixd

typedef std::vector< vectord >	vecOfvec

typedef double(*	eval_func) (unsigned int n, const double x, double gradient, void *func_data)

Enumerations
enum	innerOptAlgorithms { DIRECT, LBFGS, BOBYQA, COMBINED }

enum	McmcAlgorithms { SLICE_MCMC }

Functions
template<typename KernelType >
Kernel *	create_func ()

template<typename MeanType >
ParametricFunction *	create_func ()

template<typename CriteriaType >
Criteria *	create_func ()

double	softmax (double g, double eta)
	Softmax function. More...

void	checkNLOPTerror (nlopt_result errortype)

double	run_nlopt (nlopt::algorithm algo, eval_func fpointer, vectord &Xnext, int maxf, const std::vector< double > &vd, const std::vector< double > &vu, void *objPointer)

Variables
const size_t	MAX_INNER_EVALUATIONS = 500
	Used per dimmension.

Detailed Description

Namespace of the library interface.

Enumeration Type Documentation

◆ innerOptAlgorithms

enum bayesopt::innerOptAlgorithms

Enumerator
DIRECT	Global optimization.
LBFGS	Local, derivative based.
BOBYQA	Local, derivative free.
COMBINED	Global exploration, local refinement (hand tuned)

Definition at line 36 of file inneroptimization.hpp.

◆ McmcAlgorithms

enum bayesopt::McmcAlgorithms

Enumerator
SLICE_MCMC	Slice sampling.

Definition at line 35 of file mcmc_sampler.hpp.

Function Documentation

◆ softmax()

double bayesopt::softmax	(	double	g,
		double	eta
	)

inline

Softmax function.

Parameters

g	gain function
eta	smoothness coefficient

Returns

Definition at line 38 of file criteria_hedge.cpp.

Namespaces

Classes

Typedefs

Enumerations