This class acts as a wrapper for basic termination policies to be used by SVDCompleteIncrementalLearning.
More...
#include <complete_incremental_termination.hpp>
|
| CompleteIncrementalTermination (TerminationPolicy tPolicy=TerminationPolicy()) |
| Empty constructor. More...
|
|
template<class MatType > |
void | Initialize (const MatType &V) |
| Initializes the termination policy before stating the factorization. More...
|
|
void | Initialize (const arma::sp_mat &V) |
| Initializes the termination policy before stating the factorization. More...
|
|
bool | IsConverged (arma::mat &W, arma::mat &H) |
| Check if termination criterion is met, if the current iteration means that each point has been visited. More...
|
|
const double & | Index () const |
| Get current value of residue.
|
|
const size_t & | Iteration () const |
| Get current iteration count.
|
|
const size_t & | MaxIterations () const |
| Access upper limit of iteration count.
|
|
size_t & | MaxIterations () |
| Modify maximum number of iterations.
|
|
const TerminationPolicy & | TPolicy () const |
| Access the wrapped termination policy.
|
|
TerminationPolicy & | TPolicy () |
| Modify the wrapped termination policy.
|
|
template<class TerminationPolicy>
class mlpack::amf::CompleteIncrementalTermination< TerminationPolicy >
This class acts as a wrapper for basic termination policies to be used by SVDCompleteIncrementalLearning.
This class calls the wrapped class functions after every n calls to main class functions where n is the number of non-zero entries in the matrix being factorized. This is necessary for SVDCompleteIncrementalLearning, because otherwise IsConverged() is called after every point, which is very slow.
- See also
- AMF, SVDCompleteIncrementalLearning
◆ CompleteIncrementalTermination()
template<class TerminationPolicy >
Empty constructor.
- Parameters
-
tPolicy | object of wrapped class. |
◆ Initialize() [1/2]
template<class TerminationPolicy >
template<class MatType >
Initializes the termination policy before stating the factorization.
- Parameters
-
V | Input matrix to be factorized. |
◆ Initialize() [2/2]
template<class TerminationPolicy >
Initializes the termination policy before stating the factorization.
This is a specialization for sparse matrices.
- Parameters
-
V | Input matrix to be factorized. |
◆ IsConverged()
template<class TerminationPolicy >
Check if termination criterion is met, if the current iteration means that each point has been visited.
- Parameters
-
W | Basis matrix of output. |
H | Encoding matrix of output. |
The documentation for this class was generated from the following file: