shark::SvmShrinkingProblem< Problem > Class Template Reference
#include <shark/Algorithms/QP/SvmProblems.h>
Inheritance diagram for shark::SvmShrinkingProblem< Problem >:
Public Member Functions | |
| SvmShrinkingProblem (Problem &problem, bool shrink=true) | |
| Public Member Functions inherited from shark::BoxBasedShrinkingStrategy< SvmProblem< Problem > > | |
| BoxBasedShrinkingStrategy (ProblemT &problem, bool shrink=true) | |
| virtual void | updateSMO (std::size_t i, std::size_t j) |
| bool | shrink (double epsilon) |
| void | unshrink () |
| Unshrink the problem. | |
| void | setShrinking (bool shrinking) |
| void | setInitialSolution (RealVector const &alpha, RealVector const &gradient, RealVector const &gradientEdge) |
| Define the initial solution for the iterative solver. | |
| void | setInitialSolution (RealVector const &alpha) |
| Define the initial solution for the iterative solver. | |
| void | deactivateVariable (std::size_t i) |
| Remove the i-th example from the problem. | |
| void | scaleBoxConstraints (double factor, double variableScalingFactor) |
| Scales all box constraints by a constant factor and adapts the solution by scaling it by the same factor. | |
| virtual void | setLinear (std::size_t i, double newValue) |
| adapts the linear part of the problem and updates the internal data structures accordingly. | |
| void | flipCoordinates (std::size_t i, std::size_t j) |
| swap indizes (i,j) | |
| Public Member Functions inherited from shark::SvmProblem< Problem > | |
| SvmProblem (Problem &problem) | |
| std::size_t | dimensions () const |
| std::size_t | active () const |
| double | boxMin (std::size_t i) const |
| double | boxMax (std::size_t i) const |
| bool | isLowerBound (std::size_t i) const |
| bool | isUpperBound (std::size_t i) const |
| MatrixType & | quadratic () |
| representation of the quadratic part of the objective function | |
| double | linear (std::size_t i) const |
| double | alpha (std::size_t i) const |
| double | diagonal (std::size_t i) const |
| double | gradient (std::size_t i) const |
| std::size_t | permutation (std::size_t i) const |
| RealVector | getUnpermutedAlpha () const |
| void | updateSMO (std::size_t i, std::size_t j) |
| Does an update of SMO given a working set with indices i and j. | |
| double | functionValue () const |
| Returns the current function value of the problem. | |
| bool | shrink (double) |
| void | reshrink () |
| void | unshrink () |
| void | setInitialSolution (RealVector const &alpha, RealVector const &gradient) |
| Define the initial solution for the iterative solver. | |
| void | setInitialSolution (RealVector const &alpha) |
| Define the initial solution for the iterative solver. | |
| void | deactivateVariable (std::size_t i) |
| Remove the i-th example from the problem while taking the equality constraint into account. | |
| void | activateVariable (std::size_t i) |
| Reactivate an previously deactivated variable. | |
| void | flipCoordinates (std::size_t i, std::size_t j) |
| exchange two variables via the permutation | |
| void | scaleBoxConstraints (double factor, double variableScalingFactor) |
| Scales all box constraints by a constant factor and adapts the solution using a separate scaling. | |
| double | checkKKT () const |
Additional Inherited Members | |
| Public Types inherited from shark::BoxBasedShrinkingStrategy< SvmProblem< Problem > > | |
| typedef Problem::QpFloatType | QpFloatType |
| typedef Problem::MatrixType | MatrixType |
| typedef Problem::PreferedSelectionStrategy | PreferedSelectionStrategy |
| Public Types inherited from shark::SvmProblem< Problem > | |
| typedef Problem::QpFloatType | QpFloatType |
| typedef Problem::MatrixType | MatrixType |
| typedef LibSVMSelectionCriterion | PreferedSelectionStrategy |
| Protected Member Functions inherited from shark::SvmProblem< Problem > | |
| virtual void | applyStep (std::size_t i, std::size_t j, double step) |
| Update the problem by a proposed step i taking the box constraints into account. | |
| void | updateAlphaStatus (std::size_t i) |
| bool | testShrinkVariable (std::size_t a, double largestUp, double smallestDown) const |
| Protected Attributes inherited from shark::SvmProblem< Problem > | |
| Problem | m_problem |
| RealVector | m_gradient |
| gradient of the objective function at the current alpha | |
| std::size_t | m_active |
| std::vector< char > | m_alphaStatus |
| Stores the status, whther alpha is on the lower or upper bound, or whether it is free. | |
Detailed Description
template<class Problem>
class shark::SvmShrinkingProblem< Problem >
class shark::SvmShrinkingProblem< Problem >
Definition at line 646 of file SvmProblems.h.
Constructor & Destructor Documentation
◆ SvmShrinkingProblem()
template<class Problem >
|
inline |
Definition at line 648 of file SvmProblems.h.
The documentation for this class was generated from the following file:
- include/shark/Algorithms/QP/SvmProblems.h