ApplyProximalGradientDescent

public final class ApplyProximalGradientDescent

Update '*var' as FOBOS algorithm with fixed learning rate.

prox_v = var - alpha delta var = sign(prox_v)/(1+alphal2) max{|prox_v|-alphal1,0}

Nested Classes

class ApplyProximalGradientDescent.Options Optional attributes for ApplyProximalGradientDescent  

Constants

String OP_NAME The name of this op, as known by TensorFlow core engine

Public Methods

Output<T>
asOutput()
Returns the symbolic handle of the tensor.
static <T extends TType> ApplyProximalGradientDescent<T>
create(Scope scope, Operand<T> var, Operand<T> alpha, Operand<T> l1, Operand<T> l2, Operand<T> delta, Options... options)
Factory method to create a class wrapping a new ApplyProximalGradientDescent operation.
Output<T>
out()
Same as "var".
static ApplyProximalGradientDescent.Options
useLocking(Boolean useLocking)

Inherited Methods

Constants

public static final String OP_NAME

The name of this op, as known by TensorFlow core engine

Constant Value: "ApplyProximalGradientDescent"

Public Methods

public Output<T> asOutput ()

Returns the symbolic handle of the tensor.

Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.

public static ApplyProximalGradientDescent<T> create (Scope scope, Operand<T> var, Operand<T> alpha, Operand<T> l1, Operand<T> l2, Operand<T> delta, Options... options)

Factory method to create a class wrapping a new ApplyProximalGradientDescent operation.

Parameters
scope current scope
var Should be from a Variable().
alpha Scaling factor. Must be a scalar.
l1 L1 regularization. Must be a scalar.
l2 L2 regularization. Must be a scalar.
delta The change.
options carries optional attributes values
Returns
  • a new instance of ApplyProximalGradientDescent

public Output<T> out ()

Same as "var".

public static ApplyProximalGradientDescent.Options useLocking (Boolean useLocking)

Parameters
useLocking If True, the subtraction will be protected by a lock; otherwise the behavior is undefined, but may exhibit less contention.