Class LearningRateUpdater¶
Defined in File minibatchOptimization.h
Class Documentation¶
-
class
parpe
::
LearningRateUpdater
¶ learning rate updaters for minibatch 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 optimizationLearningRateadaptionMode
: 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
-