ApplyFtrl

Stay organized with collections Save and categorize content based on your preferences.
public final class ApplyFtrl

Update '*var' according to the Ftrl-proximal scheme.

grad_with_shrinkage = grad + 2 * l2_shrinkage * var accum_new = accum + grad * grad linear += grad_with_shrinkage - (accum_new^(-lr_power) - accum^(-lr_power)) / lr * var quadratic = 1.0 / (accum_new^(lr_power) * lr) + 2 * l2 var = (sign(linear) * l1 - linear) / quadratic if |linear| > l1 else 0.0 accum = accum_new

Nested Classes

class ApplyFtrl.Options Optional attributes for ApplyFtrl  

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> ApplyFtrl<T>
create(Scope scope, Operand<T> var, Operand<T> accum, Operand<T> linear, Operand<T> grad, Operand<T> lr, Operand<T> l1, Operand<T> l2, Operand<T> l2Shrinkage, Operand<T> lrPower, Options... options)
Factory method to create a class wrapping a new ApplyFtrl operation.
static ApplyFtrl.Options
multiplyLinearByLr(Boolean multiplyLinearByLr)
Output<T>
out()
Same as "var".
static ApplyFtrl.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: "ApplyFtrlV2"

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 ApplyFtrl<T> create (Scope scope, Operand<T> var, Operand<T> accum, Operand<T> linear, Operand<T> grad, Operand<T> lr, Operand<T> l1, Operand<T> l2, Operand<T> l2Shrinkage, Operand<T> lrPower, Options... options)

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

Parameters
scope current scope
var Should be from a Variable().
accum Should be from a Variable().
linear Should be from a Variable().
grad The gradient.
lr Scaling factor. Must be a scalar.
l1 L1 regularization. Must be a scalar.
l2 L2 shrinkage regularization. Must be a scalar.
lrPower Scaling factor. Must be a scalar.
options carries optional attributes values
Returns
  • a new instance of ApplyFtrl

public static ApplyFtrl.Options multiplyLinearByLr (Boolean multiplyLinearByLr)

public Output<T> out ()

Same as "var".

public static ApplyFtrl.Options useLocking (Boolean useLocking)

Parameters
useLocking If `True`, updating of the var and accum tensors will be protected by a lock; otherwise the behavior is undefined, but may exhibit less contention.