ANOVA kernel. More...

#include <Kernel.hpp>

Inheritance diagram for strumpack::kernel::ANOVAKernel< scalar_t >:

Collaboration diagram for strumpack::kernel::ANOVAKernel< scalar_t >:

Public Member Functions
	ANOVAKernel (DenseMatrix< scalar_t > &data, scalar_t h, scalar_t lambda, int p=1)

Public Member Functions inherited from strumpack::kernel::Kernel< scalar_t >
	Kernel (DenseM_t &data, scalar_t lambda)

virtual	~Kernel ()=default

std::size_t	n () const

std::size_t	d () const

virtual scalar_t	eval (std::size_t i, std::size_t j) const

void	operator() (const std::vector< std::size_t > &I, const std::vector< std::size_t > &J, DenseMatrix< real_t > &B) const

void	operator() (const std::vector< std::size_t > &I, const std::vector< std::size_t > &J, DenseMatrix< std::complex< real_t >> &B) const

DenseM_t	fit_HSS (std::vector< scalar_t > &labels, const HSS::HSSOptions< scalar_t > &opts)

std::vector< scalar_t >	predict (const DenseM_t &test, const DenseM_t &weights) const

DistM_t	fit_HSS (const BLACSGrid &grid, std::vector< scalar_t > &labels, const HSS::HSSOptions< scalar_t > &opts)

std::vector< scalar_t >	predict (const DenseM_t &test, const DistM_t &weights) const

DenseM_t	fit_HODLR (const MPIComm &c, std::vector< scalar_t > &labels, const HODLR::HODLROptions< scalar_t > &opts)

const DenseM_t &	data () const

DenseM_t &	data ()

std::vector< int > &	permutation ()

const std::vector< int > &	permutation () const

virtual void	permute ()

Detailed Description

template<typename scalar_t>
class strumpack::kernel::ANOVAKernel< scalar_t >

ANOVA kernel.

Implements the kernel: \( \sum_{1\leq k_1<...<k_p\leq n}k(x^{k_1},y^{k_1})\times...\times k(x^{k_p},y^{k_p}), with k(x,y)=\exp \left( -\frac{\|x-y\|_2^2}{2 h^2} \right)\), with an extra regularization parameter lambda on the diagonal. The kernel is implemented efficiently due to the recurrence relation in "Support Vector Regression with ANOVA Decomposition Kernels", 1999.

This is a subclass of Kernel. It only implements the (protected) eval_kernel_function routine, the rest of the functionality is inherited. To create your own kernel, simply copy this class, rename and change the eval_kernel_function implementation.

See also: Kernel, GaussKernel

Constructor & Destructor Documentation

◆ ANOVAKernel()

template<typename scalar_t >

strumpack::kernel::ANOVAKernel< scalar_t >::ANOVAKernel	(	DenseMatrix< scalar_t > &	data,
		scalar_t	h,
		scalar_t	lambda,
		int	p = `1`
	)

inline

Constructor of the kernel object.

Parameters

data	Data defining the kernel matrix. data.rows() is the number of features, and data.cols() is the number of data points, ie, the dimension of the kernel matrix.
h	Kernel width
lambda	Regularization parameter, added to the diagonal
p	Kernel degree (1 <= p_ <= this->d())

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

/home/pieterg/LBL/STRUMPACK_master/src/kernel/Kernel.hpp

Public Member Functions

Detailed Description

template<typename scalar_t> class strumpack::kernel::ANOVAKernel< scalar_t >

Constructor & Destructor Documentation

◆ ANOVAKernel()

template<typename scalar_t>
class strumpack::kernel::ANOVAKernel< scalar_t >