Adadelta

Value Members

1. final def !=(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

2. final def ##(): Int

   

   Definition Classes

   AnyRef → Any

3. final def ==(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

4. final def asInstanceOf[T0]: T0

   

   Definition Classes

   Any

5. def clearHistory(state: Table): Table

   

   Clear the history information in the state

   Clear the history information in the state

   Definition Classes

   Adadelta → OptimMethod

6. def clone(): AnyRef

   

   Attributes

   protected[java.lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( ... )

7. final def eq(arg0: AnyRef): Boolean

   

   Definition Classes

   AnyRef

8. def equals(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

9. def finalize(): Unit

   

   Attributes

   protected[java.lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( classOf[java.lang.Throwable] )

10. final def getClass(): Class[_]

    

    Definition Classes

    AnyRef → Any

11. def getHyperParameter(config: Table): String

    

    Get hyper parameter from config table.

    Get hyper parameter from config table.

    config

    a table contains the hyper parameter.

    Definition Classes

    OptimMethod

12. def hashCode(): Int

    

    Definition Classes

    AnyRef → Any

13. final def isInstanceOf[T0]: Boolean

    

    Definition Classes

    Any

14. final def ne(arg0: AnyRef): Boolean

    

    Definition Classes

    AnyRef

15. final def notify(): Unit

    

    Definition Classes

    AnyRef

16. final def notifyAll(): Unit

    

    Definition Classes

    AnyRef

17. def optimize(feval: (Tensor[T]) ⇒ (T, Tensor[T]), parameter: Tensor[T], config: Table, state: Table): (Tensor[T], Array[T])

    

    Adadelta implementation for SGD: http://arxiv.org/abs/1212.5701

    Adadelta implementation for SGD: http://arxiv.org/abs/1212.5701

    feval

    a function that takes a single input (X), the point of a evaluation, and returns f(X) and df/dX

    parameter

    the initial point

    config

    a table with hyper-parameters for the optimizer config("learningRate") : learning rate config("learningRateDecay") : learning rate decay config("decayRate"): decayRate, also called interpolation parameter rho config("Epsilon"): for numerical stability

    state

    a table describing the state of the optimizer; after each call the state is modified state("paramVariance") : vector of temporal variances of parameters state("accDelta"): vector of accumulated delta of gradients

    returns

    the new x vector and the function list {fx}, evaluated before the update

    Definition Classes

    Adadelta → OptimMethod

18. final def synchronized[T0](arg0: ⇒ T0): T0

    

    Definition Classes

    AnyRef

19. def toString(): String

    

    Definition Classes

    AnyRef → Any

20. def updateHyperParameter(config: Table, state: Table): Unit

    

    Update hyper parameter.

    Update hyper parameter. We have updated hyper parameter in method optimize(). But in DistriOptimizer, the method optimize() is only called on the executor side, the driver's hyper parameter is unchanged. So this method is using to update hyper parameter on the driver side.

    config

    config table.

    state

    state Table.

    returns

    A string.

    Definition Classes

    OptimMethod

21. final def wait(): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

22. final def wait(arg0: Long, arg1: Int): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

23. final def wait(arg0: Long): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )