Alternating Matrix Factorization. More...

Classes
class	AMF
	This class implements AMF (alternating matrix factorization) on the given matrix V. More...

class	AverageInitialization
	This initialization rule initializes matrix W and H to root of the average of V, perturbed with uniform noise. More...

class	CompleteIncrementalTermination
	This class acts as a wrapper for basic termination policies to be used by SVDCompleteIncrementalLearning. More...

class	GivenInitialization
	This initialization rule for AMF simply fills the W and H matrices with the matrices given to the constructor of this object. More...

class	IncompleteIncrementalTermination
	This class acts as a wrapper for basic termination policies to be used by SVDIncompleteIncrementalLearning. More...

class	MaxIterationTermination
	This termination policy only terminates when the maximum number of iterations has been reached. More...

class	MergeInitialization
	This initialization rule for AMF simply takes in two initialization rules, and initialize W with the first rule and H with the second rule. More...

class	NMFALSUpdate
	This class implements a method titled 'Alternating Least Squares' described in the following paper: More...

class	NMFMultiplicativeDistanceUpdate
	The multiplicative distance update rules for matrices W and H. More...

class	NMFMultiplicativeDivergenceUpdate
	This follows a method described in the paper 'Algorithms for Non-negative. More...

class	RandomAcolInitialization
	This class initializes the W matrix of the AMF algorithm by averaging p randomly chosen columns of V. More...

class	RandomInitialization
	This initialization rule for AMF simply fills the W and H matrices with uniform random noise in [0, 1]. More...

class	SimpleResidueTermination
	This class implements a simple residue-based termination policy. More...

class	SimpleToleranceTermination
	This class implements residue tolerance termination policy. More...

class	SVDBatchLearning
	This class implements SVD batch learning with momentum. More...

class	SVDCompleteIncrementalLearning
	This class computes SVD using complete incremental batch learning, as described in the following paper: More...

class	SVDCompleteIncrementalLearning< arma::sp_mat >
	TODO : Merge this template specialized function for sparse matrix using common row_col_iterator. More...

class	SVDIncompleteIncrementalLearning
	This class computes SVD using incomplete incremental batch learning, as described in the following paper: More...

class	ValidationRMSETermination
	This class implements validation termination policy based on RMSE index. More...

Typedefs
typedef amf::AMF< amf::SimpleResidueTermination, amf::RandomAcolInitialization<>, amf::NMFALSUpdate >	NMFALSFactorizer

template < typename MatType = arma::mat >
using	SVDBatchFactorizer = amf::AMF< amf::SimpleResidueTermination, amf::RandomAcolInitialization<>, amf::SVDBatchLearning >
	Convenience typedefs. More...

template < class MatType = arma::mat >
using	SVDCompleteIncrementalFactorizer = amf::AMF< amf::SimpleResidueTermination, amf::RandomAcolInitialization<>, amf::SVDCompleteIncrementalLearning< MatType > >
	SVDCompleteIncrementalFactorizer factorizes given matrix V into two matrices W and H by complete incremental gradient descent. More...

template < class MatType = arma::mat >
using	SVDIncompleteIncrementalFactorizer = amf::AMF< amf::SimpleResidueTermination, amf::RandomAcolInitialization<>, amf::SVDIncompleteIncrementalLearning >
	SVDIncompleteIncrementalFactorizer factorizes given matrix V into two matrices W and H by incomplete incremental gradient descent. More...

Functions
template < >
void	SVDBatchLearning::HUpdate< arma::sp_mat > (const arma::sp_mat &V, const arma::mat &W, arma::mat &H)

template < >
void	SVDBatchLearning::WUpdate< arma::sp_mat > (const arma::sp_mat &V, arma::mat &W, const arma::mat &H)
	TODO : Merge this template specialized function for sparse matrix using common row_col_iterator. More...

template < >
void	SVDIncompleteIncrementalLearning::HUpdate< arma::sp_mat > (const arma::sp_mat &V, const arma::mat &W, arma::mat &H)

template < >
void	SVDIncompleteIncrementalLearning::WUpdate< arma::sp_mat > (const arma::sp_mat &V, arma::mat &W, const arma::mat &H)
	TODO : Merge this template specialized function for sparse matrix using common row_col_iterator. More...

Detailed Description

Alternating Matrix Factorization.

Typedef Documentation

◆ NMFALSFactorizer

typedef amf::AMF<amf::SimpleResidueTermination, amf::RandomAcolInitialization<>, amf::NMFALSUpdate> NMFALSFactorizer

Definition at line 143 of file amf.hpp.

◆ SVDBatchFactorizer

using SVDBatchFactorizer = amf::AMF< amf::SimpleResidueTermination, amf::RandomAcolInitialization<>, amf::SVDBatchLearning>

Convenience typedefs.

SVDBatchFactorizer factorizes given matrix V into two matrices W and H by gradient descent. SVD batch learning is described in paper 'A Guide to singular Value Decomposition' by Chih-Chao Ma.

See also: SVDBatchLearning

Definition at line 158 of file amf.hpp.

◆ SVDCompleteIncrementalFactorizer

using SVDCompleteIncrementalFactorizer = amf::AMF< amf::SimpleResidueTermination, amf::RandomAcolInitialization<>, amf::SVDCompleteIncrementalLearning<MatType> >

SVDCompleteIncrementalFactorizer factorizes given matrix V into two matrices W and H by complete incremental gradient descent.

SVD complete incremental learning is described in paper 'A Guide to singular Value Decomposition' by Chih-Chao Ma.

See also: SVDCompleteIncrementalLearning

Definition at line 185 of file amf.hpp.

◆ SVDIncompleteIncrementalFactorizer

using SVDIncompleteIncrementalFactorizer = amf::AMF< amf::SimpleResidueTermination, amf::RandomAcolInitialization<>, amf::SVDIncompleteIncrementalLearning>

SVDIncompleteIncrementalFactorizer factorizes given matrix V into two matrices W and H by incomplete incremental gradient descent.

SVD incomplete incremental learning is described in paper 'A Guide to singular Value Decomposition' by Chih-Chao Ma.

See also: SVDIncompleteIncrementalLearning

Definition at line 172 of file amf.hpp.

Function Documentation

◆ SVDBatchLearning::HUpdate< arma::sp_mat >()

void mlpack::amf::SVDBatchLearning::HUpdate< arma::sp_mat >	(	const arma::sp_mat &	V,
		const arma::mat &	W,
		arma::mat &	H
	)

inline

Definition at line 230 of file svd_batch_learning.hpp.

◆ SVDBatchLearning::WUpdate< arma::sp_mat >()

void mlpack::amf::SVDBatchLearning::WUpdate< arma::sp_mat >	(	const arma::sp_mat &	V,
		arma::mat &	W,
		const arma::mat &	H
	)

inline

TODO : Merge this template specialized function for sparse matrix using common row_col_iterator.

WUpdate function specialization for sparse matrix

Definition at line 202 of file svd_batch_learning.hpp.

◆ SVDIncompleteIncrementalLearning::HUpdate< arma::sp_mat >()

void mlpack::amf::SVDIncompleteIncrementalLearning::HUpdate< arma::sp_mat >	(	const arma::sp_mat &	V,
		const arma::mat &	W,
		arma::mat &	H
	)

inline

Definition at line 185 of file svd_incomplete_incremental_learning.hpp.

◆ SVDIncompleteIncrementalLearning::WUpdate< arma::sp_mat >()

void mlpack::amf::SVDIncompleteIncrementalLearning::WUpdate< arma::sp_mat >	(	const arma::sp_mat &	V,
		arma::mat &	W,
		const arma::mat &	H
	)

inline

TODO : Merge this template specialized function for sparse matrix using common row_col_iterator.

template specialiazed functions for sparse matrices

Definition at line 166 of file svd_incomplete_incremental_learning.hpp.

Classes

Typedefs

Functions

Detailed Description

Typedef Documentation

◆ NMFALSFactorizer

◆ SVDBatchFactorizer

◆ SVDCompleteIncrementalFactorizer

◆ SVDIncompleteIncrementalFactorizer

Function Documentation

◆ SVDBatchLearning::HUpdate< arma::sp_mat >()

◆ SVDBatchLearning::WUpdate< arma::sp_mat >()

◆ SVDIncompleteIncrementalLearning::HUpdate< arma::sp_mat >()

◆ SVDIncompleteIncrementalLearning::WUpdate< arma::sp_mat >()