Class LearningRateUpdater

Class Documentation

class LearningRateUpdater

learning rate updaters for mini-batch optimizers

The LearningRateUpdater provides the possibility to reduce the learning rate per epoch and makes it possible to adapt the learning rate according to success or failure of the ODE solver.

Public Functions

LearningRateUpdater(int maxEpochs, learningRateInterp learningRateInterpMode)

Update the learning rate.

Parameters:

  • maxEpochs – Maximum number of epochs in optimization

  • LearningRateadaptionMode – Type of interpolation between startLearningRate and endLearningRate

void updateLearningRate(int iteration)

Update function, to be called in every epoch or optimization iteration

void reduceLearningRate()

Update function, to be called if parameter update did not work well

void increaseLearningRate()

Update function, to be called if parameter update worked well

double getCurrentLearningRate()

Function to retrieve the learning rate

void setReductionFactor(double newReductionFactor)

Function to set the reduction factor directly

void setMaxEpochs(int newMaxEpochs)

Function to set the new maximum epoch number

void setStartLearningRate(double learningRate)

Function to set start learning rate

void setEndLearningRate(double learningRate)

Function to set end learning rate