Package org.apache.ignite.ml.optimization

Contains implementations of optimization algorithms and related classes.

See: Description

Interface Summary

Interface	Description
Parametrized<M extends Parametrized<M>>	Interface for parametrized models.
SmoothParametrized<M extends Parametrized<M>>	Interface for models which are smooth functions of their parameters.
Updater	Weights updater applied on every gradient descent step to decide how weights should be changed.

Class Summary

Class	Description
BarzilaiBorweinUpdater	Updater based in Barzilai-Borwein method which guarantees convergence.
LossFunctions	Class containing popular loss functions.
SimpleUpdater	Simple updater with fixed learning rate which doesn't guarantee convergence.

Package org.apache.ignite.ml.optimization Description

Contains implementations of optimization algorithms and related classes.