SHOGUN
v2.0.0
|
Class SubGradientSVM trains a linear classifier called Linear Programming Machine, i.e. a SVM using a norm regularizer.
It solves the following optimization problem using subgradient descent.
Note that this implementation is not very stable numerically for a large number of dimensions. Also note that currently CPLEX is required to solve this problem.
Definition at line 48 of file SubGradientLPM.h.
Public Attributes | |
SGIO * | io |
Parallel * | parallel |
Version * | version |
Parameter * | m_parameters |
Parameter * | m_model_selection_parameters |
ParameterMap * | m_parameter_map |
uint32_t | m_hash |
Protected Member Functions | |
int32_t | find_active (int32_t num_feat, int32_t num_vec, int32_t &num_active, int32_t &num_bound) |
void | update_active (int32_t num_feat, int32_t num_vec) |
float64_t | compute_objective (int32_t num_feat, int32_t num_vec) |
compute svm objective | |
float64_t | compute_min_subgradient (int32_t num_feat, int32_t num_vec, int32_t num_active, int32_t num_bound) |
float64_t | line_search (int32_t num_feat, int32_t num_vec) |
performs a line search to determine step size | |
void | compute_projection (int32_t num_feat, int32_t num_vec) |
compute projection | |
void | update_projection (float64_t alpha, int32_t num_vec) |
only computes updates on the projection | |
void | init (int32_t num_vec, int32_t num_feat) |
alloc helper arrays | |
void | cleanup () |
de-alloc helper arrays | |
virtual const char * | get_name () const |
virtual bool | train_machine (CFeatures *data=NULL) |
virtual SGVector< float64_t > | apply_get_outputs (CFeatures *data) |
virtual void | store_model_features () |
virtual bool | is_label_valid (CLabels *lab) const |
virtual bool | train_require_labels () const |
virtual TParameter * | migrate (DynArray< TParameter * > *param_base, const SGParamInfo *target) |
virtual void | one_to_one_migration_prepare (DynArray< TParameter * > *param_base, const SGParamInfo *target, TParameter *&replacement, TParameter *&to_migrate, char *old_name=NULL) |
virtual void | load_serializable_pre () throw (ShogunException) |
virtual void | load_serializable_post () throw (ShogunException) |
virtual void | save_serializable_pre () throw (ShogunException) |
virtual void | save_serializable_post () throw (ShogunException) |
virtual bool | update_parameter_hash () |
Protected Attributes | |
float64_t | C1 |
float64_t | C2 |
float64_t | epsilon |
float64_t | work_epsilon |
float64_t | autoselected_epsilon |
int32_t | qpsize |
int32_t | qpsize_max |
int32_t | qpsize_limit |
bool | use_bias |
int32_t | last_it_noimprovement |
int32_t | num_it_noimprovement |
uint8_t * | active |
uint8_t * | old_active |
int32_t * | idx_active |
int32_t * | idx_bound |
int32_t | delta_active |
int32_t | delta_bound |
float64_t * | proj |
float64_t * | tmp_proj |
int32_t * | tmp_proj_idx |
float64_t * | sum_CXy_active |
float64_t * | v |
float64_t * | old_v |
float64_t | sum_Cy_active |
int32_t | pos_idx |
int32_t | neg_idx |
int32_t | zero_idx |
int32_t * | w_pos |
int32_t * | w_zero |
int32_t * | w_neg |
float64_t * | grad_w |
float64_t | grad_b |
float64_t * | grad_proj |
float64_t * | hinge_point |
int32_t * | hinge_idx |
float64_t * | beta |
CCplex * | solver |
float64_t | lpmtim |
SGVector< float64_t > | w |
float64_t | bias |
CDotFeatures * | features |
float64_t | m_max_train_time |
CLabels * | m_labels |
ESolverType | m_solver_type |
bool | m_store_model_features |
bool | m_data_locked |
CSubGradientLPM | ( | ) |
Definition at line 29 of file SubGradientLPM.cpp.
CSubGradientLPM | ( | float64_t | C, |
CDotFeatures * | traindat, | ||
CLabels * | trainlab | ||
) |
Definition at line 35 of file SubGradientLPM.cpp.
|
virtual |
Definition at line 45 of file SubGradientLPM.cpp.
apply machine to data if data is not specified apply to the current features
data | (test)data to be classified |
Definition at line 162 of file Machine.cpp.
|
virtualinherited |
apply linear machine to data for binary classification problem
data | (test)data to be classified |
Reimplemented from CMachine.
Reimplemented in CDomainAdaptationSVMLinear.
Definition at line 57 of file LinearMachine.cpp.
apply get outputs
data | features to compute outputs |
Reimplemented in CMultitaskLinearMachine, and CFeatureBlockLogisticRegression.
Definition at line 63 of file LinearMachine.cpp.
|
virtualinherited |
apply machine to data in means of latent problem
Reimplemented in CLinearLatentMachine.
Definition at line 242 of file Machine.cpp.
Applies a locked machine on a set of indices. Error if machine is not locked
indices | index vector (of locked features) that is predicted |
Definition at line 197 of file Machine.cpp.
|
virtualinherited |
applies a locked machine on a set of indices for binary problems
Reimplemented in CKernelMachine, CMultitaskLinearMachine, and CMultitaskCompositeMachine.
Definition at line 248 of file Machine.cpp.
|
virtualinherited |
applies a locked machine on a set of indices for latent problems
Definition at line 276 of file Machine.cpp.
|
virtualinherited |
applies a locked machine on a set of indices for multiclass problems
Definition at line 262 of file Machine.cpp.
|
virtualinherited |
applies a locked machine on a set of indices for regression problems
Reimplemented in CKernelMachine.
Definition at line 255 of file Machine.cpp.
|
virtualinherited |
applies a locked machine on a set of indices for structured problems
Definition at line 269 of file Machine.cpp.
|
virtualinherited |
apply machine to data in means of multiclass classification problem
Reimplemented in CDistanceMachine, CMulticlassMachine, CKNN, CVwConditionalProbabilityTree, CGaussianNaiveBayes, CConjugateIndex, CConditionalProbabilityTree, CQDA, and CRelaxedTree.
Definition at line 230 of file Machine.cpp.
|
virtualinherited |
applies to one vector
Reimplemented from CMachine.
Reimplemented in CMultitaskLinearMachine, CMultitaskLogisticRegression, CMultitaskLeastSquaresRegression, and CFeatureBlockLogisticRegression.
Definition at line 46 of file LinearMachine.cpp.
|
virtualinherited |
apply linear machine to data for regression problem
data | (test)data to be classified |
Reimplemented from CMachine.
Definition at line 51 of file LinearMachine.cpp.
|
virtualinherited |
apply machine to data in means of SO classification problem
Reimplemented in CLinearStructuredOutputMachine.
Definition at line 236 of file Machine.cpp.
|
inherited |
Builds a dictionary of all parameters in SGObject as well of those of SGObjects that are parameters of this object. Dictionary maps parameters to the objects that own them.
dict | dictionary of parameters to be built. |
Definition at line 1204 of file SGObject.cpp.
|
protected |
de-alloc helper arrays
Definition at line 502 of file SubGradientLPM.cpp.
|
virtualinherited |
|
protected |
compute minimum norm subgradient return norm of minimum norm subgradient
Definition at line 326 of file SubGradientLPM.cpp.
|
protected |
compute svm objective
Definition at line 412 of file SubGradientLPM.cpp.
|
protected |
compute projection
Definition at line 425 of file SubGradientLPM.cpp.
Locks the machine on given labels and data. After this call, only train_locked and apply_locked may be called
Only possible if supports_locking() returns true
labs | labels used for locking |
features | features used for locking |
Reimplemented in CKernelMachine.
Definition at line 122 of file Machine.cpp.
|
virtualinherited |
Unlocks a locked machine and restores previous state
Reimplemented in CKernelMachine.
Definition at line 153 of file Machine.cpp.
|
virtualinherited |
A deep copy. All the instance variables will also be copied.
Definition at line 131 of file SGObject.h.
|
protected |
returns number of changed constraints for precision work_epsilon and fills active array
Definition at line 50 of file SubGradientLPM.cpp.
|
virtualinherited |
get bias
Reimplemented in CMultitaskLinearMachine.
Definition at line 104 of file LinearMachine.h.
bool get_bias_enabled | ( | ) |
Definition at line 73 of file SubGradientLPM.h.
float64_t get_C1 | ( | ) |
Definition at line 69 of file SubGradientLPM.h.
float64_t get_C2 | ( | ) |
Definition at line 70 of file SubGradientLPM.h.
|
virtual |
get classifier type
Reimplemented from CMachine.
Definition at line 59 of file SubGradientLPM.h.
float64_t get_epsilon | ( | ) |
Definition at line 76 of file SubGradientLPM.h.
|
virtualinherited |
|
inherited |
|
inherited |
|
inherited |
|
virtualinherited |
|
virtualinherited |
returns type of problem machine solves
Reimplemented in CBaseMulticlassMachine.
|
inherited |
|
inherited |
Definition at line 1108 of file SGObject.cpp.
|
inherited |
Returns description of a given parameter string, if it exists. SG_ERROR otherwise
param_name | name of the parameter |
Definition at line 1132 of file SGObject.cpp.
|
inherited |
Returns index of model selection parameter with provided index
param_name | name of model selection parameter |
Definition at line 1145 of file SGObject.cpp.
|
protectedvirtual |
Reimplemented from CLinearMachine.
Definition at line 120 of file SubGradientLPM.h.
int32_t get_qpsize | ( | ) |
Definition at line 79 of file SubGradientLPM.h.
int32_t get_qpsize_max | ( | ) |
Definition at line 82 of file SubGradientLPM.h.
|
inherited |
get w
Reimplemented in CMultitaskLinearMachine.
Definition at line 77 of file LinearMachine.h.
|
protected |
alloc helper arrays
Definition at line 436 of file SubGradientLPM.cpp.
|
inherited |
|
virtualinherited |
If the SGSerializable is a class template then TRUE will be returned and GENERIC is set to the type of the generic.
generic | set to the type of the generic if returning TRUE |
Definition at line 278 of file SGObject.cpp.
|
protectedvirtualinherited |
check whether the labels is valid.
Subclasses can override this to implement their check of label types.
lab | the labels being checked, guaranteed to be non-NULL |
Reimplemented in CBaseMulticlassMachine.
|
protected |
performs a line search to determine step size
Definition at line 243 of file SubGradientLPM.cpp.
|
inherited |
maps all parameters of this instance to the provided file version and loads all parameter data from the file into an array, which is sorted (basically calls load_file_parameter(...) for all parameters and puts all results into a sorted array)
file_version | parameter version of the file |
current_version | version from which mapping begins (you want to use VERSION_PARAMETER for this in most cases) |
file | file to load from |
prefix | prefix for members |
Definition at line 679 of file SGObject.cpp.
|
inherited |
loads some specified parameters from a file with a specified version The provided parameter info has a version which is recursively mapped until the file parameter version is reached. Note that there may be possibly multiple parameters in the mapping, therefore, a set of TParameter instances is returned
param_info | information of parameter |
file_version | parameter version of the file, must be <= provided parameter version |
file | file to load from |
prefix | prefix for members |
Definition at line 523 of file SGObject.cpp.
|
virtualinherited |
Load this object from file. If it will fail (returning FALSE) then this object will contain inconsistent data and should not be used!
file | where to load from |
prefix | prefix for members |
param_version | (optional) a parameter version different to (this is mainly for testing, better do not use) |
Reimplemented in CModelSelectionParameters.
Definition at line 354 of file SGObject.cpp.
|
protectedvirtualinherited |
Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_POST is called.
ShogunException | Will be thrown if an error occurres. |
Reimplemented in CKernel, CWeightedDegreePositionStringKernel, CList, CAlphabet, CLinearHMM, CGaussianKernel, CANOVAKernel, CInverseMultiQuadricKernel, CCircularKernel, and CExponentialKernel.
Definition at line 1033 of file SGObject.cpp.
|
protectedvirtualinherited |
Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_PRE is called.
ShogunException | Will be thrown if an error occurres. |
Definition at line 1028 of file SGObject.cpp.
MACHINE_PROBLEM_TYPE | ( | PT_BINARY | ) |
|
inherited |
Takes a set of TParameter instances (base) with a certain version and a set of target parameter infos and recursively maps the base level wise to the current version using CSGObject::migrate(...). The base is replaced. After this call, the base version containing parameters should be of same version/type as the initial target parameter infos. Note for this to work, the migrate methods and all the internal parameter mappings have to match
param_base | set of TParameter instances that are mapped to the provided target parameter infos |
base_version | version of the parameter base |
target_param_infos | set of SGParamInfo instances that specify the target parameter base |
Definition at line 717 of file SGObject.cpp.
|
protectedvirtualinherited |
creates a new TParameter instance, which contains migrated data from the version that is provided. The provided parameter data base is used for migration, this base is a collection of all parameter data of the previous version. Migration is done FROM the data in param_base TO the provided param info Migration is always one version step. Method has to be implemented in subclasses, if no match is found, base method has to be called.
If there is an element in the param_base which equals the target, a copy of the element is returned. This represents the case when nothing has changed and therefore, the migrate method is not overloaded in a subclass
param_base | set of TParameter instances to use for migration |
target | parameter info for the resulting TParameter |
Definition at line 923 of file SGObject.cpp.
|
protectedvirtualinherited |
This method prepares everything for a one-to-one parameter migration. One to one here means that only ONE element of the parameter base is needed for the migration (the one with the same name as the target). Data is allocated for the target (in the type as provided in the target SGParamInfo), and a corresponding new TParameter instance is written to replacement. The to_migrate pointer points to the single needed TParameter instance needed for migration. If a name change happened, the old name may be specified by old_name. In addition, the m_delete_data flag of to_migrate is set to true. So if you want to migrate data, the only thing to do after this call is converting the data in the m_parameter fields. If unsure how to use - have a look into an example for this. (base_migration_type_conversion.cpp for example)
param_base | set of TParameter instances to use for migration |
target | parameter info for the resulting TParameter |
replacement | (used as output) here the TParameter instance which is returned by migration is created into |
to_migrate | the only source that is used for migration |
old_name | with this parameter, a name change may be specified |
Definition at line 864 of file SGObject.cpp.
post lock
Reimplemented in CMultitaskLinearMachine, and CMultitaskCompositeMachine.
|
inherited |
prints all parameter registered for model selection and their type
Definition at line 1084 of file SGObject.cpp.
|
virtualinherited |
prints registered parameters out
prefix | prefix for members |
Definition at line 290 of file SGObject.cpp.
|
virtualinherited |
Save this object to file.
file | where to save the object; will be closed during returning if PREFIX is an empty string. |
prefix | prefix for members |
param_version | (optional) a parameter version different to (this is mainly for testing, better do not use) |
Reimplemented in CModelSelectionParameters.
Definition at line 296 of file SGObject.cpp.
|
protectedvirtualinherited |
Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_POST is called.
ShogunException | Will be thrown if an error occurres. |
Reimplemented in CKernel.
Definition at line 1043 of file SGObject.cpp.
|
protectedvirtualinherited |
Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_PRE is called.
ShogunException | Will be thrown if an error occurres. |
Reimplemented in CKernel.
Definition at line 1038 of file SGObject.cpp.
|
virtualinherited |
set bias
b | new bias |
Reimplemented in CMultitaskLinearMachine.
Definition at line 95 of file LinearMachine.h.
void set_bias_enabled | ( | bool | enable_bias | ) |
Definition at line 72 of file SubGradientLPM.h.
set C
c_neg | new C constant for negatively labeled examples |
c_pos | new C constant for positively labeled examples |
Definition at line 67 of file SubGradientLPM.h.
void set_epsilon | ( | float64_t | eps | ) |
Definition at line 75 of file SubGradientLPM.h.
|
virtualinherited |
set features
feat | features to set |
Reimplemented in CLDA, CLPBoost, and CLPM.
Definition at line 113 of file LinearMachine.h.
|
inherited |
set generic type to T
Definition at line 41 of file SGObject.cpp.
|
inherited |
|
inherited |
set the parallel object
parallel | parallel object to use |
Definition at line 230 of file SGObject.cpp.
|
inherited |
set the version object
version | version object to use |
Definition at line 265 of file SGObject.cpp.
|
virtualinherited |
set labels
lab | labels |
Reimplemented in CRelaxedTree, and CMulticlassMachine.
Definition at line 75 of file Machine.cpp.
|
inherited |
set maximum training time
t | maximimum training time |
Definition at line 92 of file Machine.cpp.
void set_qpsize | ( | int32_t | q | ) |
Definition at line 78 of file SubGradientLPM.h.
void set_qpsize_max | ( | int32_t | q | ) |
Definition at line 81 of file SubGradientLPM.h.
|
inherited |
|
virtualinherited |
Setter for store-model-features-after-training flag
store_model | whether model should be stored after training |
Definition at line 117 of file Machine.cpp.
set w
src_w | new w |
Reimplemented in CMultitaskLinearMachine.
Definition at line 86 of file LinearMachine.h.
|
virtualinherited |
A shallow copy. All the SGObject instance variables will be simply assigned and SG_REF-ed.
Reimplemented in CGaussianKernel.
Definition at line 122 of file SGObject.h.
|
protectedvirtualinherited |
Stores feature data of underlying model. Does nothing because Linear machines store the normal vector of the separating hyperplane and therefore the model anyway
Reimplemented from CMachine.
Definition at line 171 of file LinearMachine.h.
|
virtualinherited |
Reimplemented in CKernelMachine, CMultitaskLinearMachine, and CMultitaskCompositeMachine.
|
virtualinherited |
train machine
data | training data (parameter can be avoided if distance or kernel-based classifiers are used and distance/kernels are initialized with train data). If flag is set, model features will be stored after training. |
Reimplemented in CRelaxedTree, CSGDQN, and COnlineSVMSGD.
Definition at line 49 of file Machine.cpp.
Trains a locked machine on a set of indices. Error if machine is not locked
NOT IMPLEMENTED
indices | index vector (of locked features) that is used for training |
Reimplemented in CKernelMachine, CMultitaskLinearMachine, and CMultitaskCompositeMachine.
|
protectedvirtual |
train classifier
data | training data (parameter can be avoided if distance or kernel-based classifiers are used and distance/kernels are initialized with train data) |
Reimplemented from CMachine.
Definition at line 542 of file SubGradientLPM.cpp.
|
protectedvirtualinherited |
returns whether machine require labels for training
Reimplemented in COnlineLinearMachine, CKMeans, CHierarchical, CLinearLatentMachine, CVwConditionalProbabilityTree, CConditionalProbabilityTree, and CLibSVMOneClass.
|
inherited |
unset generic type
this has to be called in classes specializing a template class
Definition at line 285 of file SGObject.cpp.
|
protected |
swaps the active / old_active and computes idx_active, idx_bound and sum_CXy_active arrays and the sum_Cy_active variable
Definition at line 221 of file SubGradientLPM.cpp.
|
protectedvirtualinherited |
Updates the hash of current parameter combination.
Definition at line 237 of file SGObject.cpp.
|
protected |
only computes updates on the projection
Definition at line 431 of file SubGradientLPM.cpp.
|
protected |
Definition at line 148 of file SubGradientLPM.h.
|
protected |
Definition at line 138 of file SubGradientLPM.h.
|
protected |
Definition at line 178 of file SubGradientLPM.h.
|
protectedinherited |
bias
Definition at line 181 of file LinearMachine.h.
|
protected |
Definition at line 134 of file SubGradientLPM.h.
|
protected |
Definition at line 135 of file SubGradientLPM.h.
|
protected |
Definition at line 152 of file SubGradientLPM.h.
|
protected |
Definition at line 153 of file SubGradientLPM.h.
|
protected |
Definition at line 136 of file SubGradientLPM.h.
|
protectedinherited |
features
Definition at line 183 of file LinearMachine.h.
|
protected |
Definition at line 172 of file SubGradientLPM.h.
|
protected |
Definition at line 173 of file SubGradientLPM.h.
|
protected |
Definition at line 171 of file SubGradientLPM.h.
|
protected |
Definition at line 175 of file SubGradientLPM.h.
|
protected |
Definition at line 174 of file SubGradientLPM.h.
|
protected |
Definition at line 150 of file SubGradientLPM.h.
|
protected |
Definition at line 151 of file SubGradientLPM.h.
|
inherited |
io
Definition at line 462 of file SGObject.h.
|
protected |
Definition at line 144 of file SubGradientLPM.h.
|
protected |
Definition at line 181 of file SubGradientLPM.h.
|
protectedinherited |
|
inherited |
Hash of parameter values
Definition at line 480 of file SGObject.h.
|
protectedinherited |
|
inherited |
model selection parameters
Definition at line 474 of file SGObject.h.
|
inherited |
map for different parameter versions
Definition at line 477 of file SGObject.h.
|
inherited |
parameters
Definition at line 471 of file SGObject.h.
|
protectedinherited |
|
protectedinherited |
|
protected |
Definition at line 166 of file SubGradientLPM.h.
|
protected |
Definition at line 145 of file SubGradientLPM.h.
|
protected |
Definition at line 149 of file SubGradientLPM.h.
|
protected |
Definition at line 161 of file SubGradientLPM.h.
|
inherited |
parallel
Definition at line 465 of file SGObject.h.
|
protected |
Definition at line 165 of file SubGradientLPM.h.
|
protected |
Definition at line 154 of file SubGradientLPM.h.
|
protected |
Definition at line 139 of file SubGradientLPM.h.
|
protected |
Definition at line 141 of file SubGradientLPM.h.
|
protected |
Definition at line 140 of file SubGradientLPM.h.
|
protected |
Definition at line 180 of file SubGradientLPM.h.
|
protected |
Definition at line 159 of file SubGradientLPM.h.
|
protected |
Definition at line 162 of file SubGradientLPM.h.
|
protected |
Definition at line 155 of file SubGradientLPM.h.
|
protected |
Definition at line 156 of file SubGradientLPM.h.
|
protected |
Definition at line 142 of file SubGradientLPM.h.
|
protected |
Definition at line 160 of file SubGradientLPM.h.
|
inherited |
version
Definition at line 468 of file SGObject.h.
w
Definition at line 179 of file LinearMachine.h.
|
protected |
Definition at line 170 of file SubGradientLPM.h.
|
protected |
Definition at line 168 of file SubGradientLPM.h.
|
protected |
Definition at line 169 of file SubGradientLPM.h.
|
protected |
Definition at line 137 of file SubGradientLPM.h.
|
protected |
Definition at line 167 of file SubGradientLPM.h.