BayesOpt
bayesopt::PosteriorModel Class Referenceabstract

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

#include <posteriormodel.hpp>

+ Inheritance diagram for bayesopt::PosteriorModel:
+ Collaboration diagram for bayesopt::PosteriorModel:

Public Member Functions

 PosteriorModel (size_t dim, Parameters params, randEngine &eng)
 Constructor. More...
 
virtual ~PosteriorModel ()
 Default destructor.
 
virtual void updateHyperParameters ()=0
 
virtual void fitSurrogateModel ()=0
 
virtual void updateSurrogateModel ()=0
 
virtual double evaluateCriteria (const vectord &query)=0
 
virtual void updateCriteria (const vectord &query)=0
 
virtual bool criteriaRequiresComparison ()=0
 
virtual void setFirstCriterium ()=0
 
virtual bool setNextCriterium (const vectord &prevResult)=0
 
virtual std::string getBestCriteria (vectord &best)=0
 
void setSamples (const matrixd &x, const vectord &y)
 
void setSamples (const matrixd &x)
 
void setSamples (const vectord &y)
 
void setSample (const vectord &x, double y)
 
void addSample (const vectord &x, double y)
 
double getValueAtMinimum ()
 
vectord getPointAtMinimum ()
 
void plotDataset (TLogLevel level)
 
const DatasetgetData ()
 
virtual ProbabilityDistributiongetPrediction (const vectord &query)=0
 

Static Public Member Functions

static PosteriorModelcreate (size_t dim, Parameters params, randEngine &eng)
 

Protected Attributes

Parameters mParameters
 Configuration parameters.
 
size_t mDims
 Number of dimensions.
 
Dataset mData
 Dataset (x-> inputs, y-> labels/output)
 
MeanModel mMean
 

Detailed Description

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

Definition at line 43 of file posteriormodel.hpp.


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