Uses of Interface
org.tribuo.common.sgd.SGDObjective
Package
Description
Provides infrastructure for Stochastic Gradient Descent for classification problems.
Provides an implementation of a classification factorization machine using Stochastic Gradient Descent.
Provides an implementation of a classification linear model using Stochastic Gradient Descent.
Provides classification loss functions for Stochastic Gradient Descent.
Provides the base classes for models trained with stochastic gradient descent.
Provides infrastructure for Stochastic Gradient Descent for multi-label classification problems.
Provides an implementation of a multi-label classification factorization machine model using Stochastic Gradient Descent.
Provides an implementation of a multi-label classification linear model using Stochastic Gradient Descent.
Provides multi-label classification loss functions for Stochastic Gradient Descent.
Provides infrastructure for Stochastic Gradient Descent based regression models.
Provides an implementation of factorization machines for regression using Stochastic Gradient Descent.
Provides an implementation of linear regression using Stochastic Gradient Descent.
Provides regression loss functions for Stochastic Gradient Descent.
-
Uses of SGDObjective in org.tribuo.classification.sgd
Modifier and TypeInterfaceDescriptioninterface
An interface for single label prediction objectives. -
Uses of SGDObjective in org.tribuo.classification.sgd.fm
Modifier and TypeMethodDescriptionprotected SGDObjective<Integer>
FMClassificationTrainer.getObjective()
-
Uses of SGDObjective in org.tribuo.classification.sgd.linear
Modifier and TypeMethodDescriptionprotected SGDObjective<Integer>
LinearSGDTrainer.getObjective()
-
Uses of SGDObjective in org.tribuo.classification.sgd.objectives
Modifier and TypeClassDescriptionclass
Hinge loss, scores the correct value margin and any incorrect predictions -margin.class
A multiclass version of the log loss. -
Uses of SGDObjective in org.tribuo.common.sgd
Modifier and TypeMethodDescriptionprotected abstract SGDObjective<U>
AbstractSGDTrainer.getObjective()
Returns the objective used by this trainer. -
Uses of SGDObjective in org.tribuo.multilabel.sgd
Modifier and TypeInterfaceDescriptioninterface
An interface for multi-label prediction objectives. -
Uses of SGDObjective in org.tribuo.multilabel.sgd.fm
Modifier and TypeMethodDescriptionprotected SGDObjective<SGDVector>
FMMultiLabelTrainer.getObjective()
-
Uses of SGDObjective in org.tribuo.multilabel.sgd.linear
Modifier and TypeMethodDescriptionprotected SGDObjective<SGDVector>
LinearSGDTrainer.getObjective()
-
Uses of SGDObjective in org.tribuo.multilabel.sgd.objectives
Modifier and TypeClassDescriptionfinal class
A multilabel version of binary cross entropy loss which expects logits.final class
Hinge loss, scores the correct value margin and any incorrect predictions -margin. -
Uses of SGDObjective in org.tribuo.regression.sgd
Modifier and TypeInterfaceDescriptioninterface
An interface for regression objectives. -
Uses of SGDObjective in org.tribuo.regression.sgd.fm
Modifier and TypeMethodDescriptionprotected SGDObjective<DenseVector>
FMRegressionTrainer.getObjective()
-
Uses of SGDObjective in org.tribuo.regression.sgd.linear
Modifier and TypeMethodDescriptionprotected SGDObjective<DenseVector>
LinearSGDTrainer.getObjective()
-
Uses of SGDObjective in org.tribuo.regression.sgd.objectives
Modifier and TypeClassDescriptionclass
Absolute loss (i.e., l1).class
Huber loss, i.e., a mixture of l2 and l1 losses.class
Squared loss, i.e., l2.