Class LinearSGDTrainer

java.lang.Object
org.tribuo.classification.sgd.linear.LinearSGDTrainer
All Implemented Interfaces:
com.oracle.labs.mlrg.olcut.config.Configurable, com.oracle.labs.mlrg.olcut.provenance.Provenancable<TrainerProvenance>, Trainer<Label>, WeightedExamples
Direct Known Subclasses:
LogisticRegressionTrainer
public class LinearSGDTrainer extends Object implements Trainer<Label>, WeightedExamples
A trainer for a linear model which uses SGD.

See: 

 Bottou L.
 "Large-Scale Machine Learning with Stochastic Gradient Descent"
 Proceedings of COMPSTAT, 2010.

  • Constructor Details

    • LinearSGDTrainer

      public LinearSGDTrainer(LabelObjective objective, StochasticGradientOptimiser optimiser, int epochs, int loggingInterval, int minibatchSize, long seed)
      Constructs an SGD trainer for a linear model.
      Parameters:
      objective - The objective function to optimise.
      optimiser - The gradient optimiser to use.
      epochs - The number of epochs (complete passes through the training data).
      loggingInterval - Log the loss after this many iterations. If -1 don't log anything.
      minibatchSize - The size of any minibatches.
      seed - A seed for the random number generator, used to shuffle the examples before each epoch.

    • LinearSGDTrainer

      public LinearSGDTrainer(LabelObjective objective, StochasticGradientOptimiser optimiser, int epochs, int loggingInterval, long seed)
      Sets the minibatch size to 1.
      Parameters:
      objective - The objective function to optimise.
      optimiser - The gradient optimiser to use.
      epochs - The number of epochs (complete passes through the training data).
      loggingInterval - Log the loss after this many iterations. If -1 don't log anything.
      seed - A seed for the random number generator, used to shuffle the examples before each epoch.

    • LinearSGDTrainer

      public LinearSGDTrainer(LabelObjective objective, StochasticGradientOptimiser optimiser, int epochs, long seed)
      Sets the minibatch size to 1 and the logging interval to 1000.
      Parameters:
      objective - The objective function to optimise.
      optimiser - The gradient optimiser to use.
      epochs - The number of epochs (complete passes through the training data).
      seed - A seed for the random number generator, used to shuffle the examples before each epoch.

  • Method Details

    • postConfig

      public void postConfig()
      Specified by:
      postConfig in interface com.oracle.labs.mlrg.olcut.config.Configurable

    • setShuffle

      public void setShuffle(boolean shuffle)
      Turn on or off shuffling of examples.

      This isn't exposed in the constructor as it defaults to on. This method should only be used for debugging.

      Parameters:
      shuffle - If true shuffle the examples, if false leave them in their current order.

    • train

      public Model<Label> train(Dataset<Label> examples, Map<String, com.oracle.labs.mlrg.olcut.provenance.Provenance> runProvenance)
      Description copied from interface: Trainer
      Trains a predictive model using the examples in the given data set.
      Specified by:
      train in interface Trainer<Label>
      Parameters:
      examples - the data set containing the examples.
      runProvenance - Training run specific provenance (e.g., fold number).
      Returns:
      a predictive model that can be used to generate predictions for new examples.

    • getInvocationCount

      public int getInvocationCount()
      Description copied from interface: Trainer
      The number of times this trainer instance has had it's train method invoked.

      This is used to determine how many times the trainer's RNG has been accessed to ensure replicability in the random number stream.

      Specified by:
      getInvocationCount in interface Trainer<Label>
      Returns:
      The number of train invocations.

    • toString

      public String toString()
      Overrides:
      toString in class Object

    • getProvenance

      public TrainerProvenance getProvenance()
      Specified by:
      getProvenance in interface com.oracle.labs.mlrg.olcut.provenance.Provenancable<TrainerProvenance>