Dakota  Version
Explore and Predict with Confidence
Public Member Functions | Private Attributes | List of all members
DerivInformedPropCovTK< V, M > Class Template Reference

Dakota transition kernel that updates proposal covariance based on derivatives (for random walk case) More...

Public Member Functions

 DerivInformedPropCovTK (const char *prefix, const QUESO::VectorSpace< V, M > &vectorSpace, const std::vector< double > &scales, const M &covMatrix, NonDQUESOBayesCalibration *queso_instance)
 Constructor for derivative-informed proposal covariance.
 
virtual ~DerivInformedPropCovTK ()
 Destructor for derivative-informed proposal covariance.
 
virtual void updateTK () override
 update the transition kernel with new covariance information
 
virtual bool covMatrixIsDirty () override
 whether the covariance matrix has been updated
 
virtual void cleanCovMatrix () override
 dependent algorithms have taken necessary cleanup actions
 

Private Attributes

const QUESO::VectorSpace< V, M > & m_vectorSpace
 calibration parameter vector space (note: hides base class member)
 
bool covIsDirty
 whether we've updated the proposal covariance
 
unsigned int chainIndex
 index into current chain position
 
NonDQUESOBayesCalibrationnonDQUESOInstance
 Dakota QUESO instance for callbacks.
 

Detailed Description

template<class V, class M>
class Dakota::DerivInformedPropCovTK< V, M >

Dakota transition kernel that updates proposal covariance based on derivatives (for random walk case)


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