Have a question? Connect with the community at the TensorFlow Forum Visit Forum

SparseApplyProximalGradientDescent

public final class SparseApplyProximalGradientDescent

Sparse update '*var' as FOBOS algorithm with fixed learning rate.

That is for rows we have grad for, we update var as follows:

$$prox_v = var - alpha grad$$
$$var = sign(prox_v)/(1+alpha l2) max{|prox_v|-alpha l1,0}$$

Nested Classes

class SparseApplyProximalGradientDescent.Options Optional attributes for SparseApplyProximalGradientDescent

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 > SparseApplyProximalGradientDescent <T>
create ( Scope scope, Operand <T> var, Operand <T> alpha, Operand <T> l1, Operand <T> l2, Operand <T> grad, Operand <? extends TNumber > indices, Options... options)
Factory method to create a class wrapping a new SparseApplyProximalGradientDescent operation.
Output <T>
out ()
Same as "var".
static SparseApplyProximalGradientDescent.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: "SparseApplyProximalGradientDescent"

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 SparseApplyProximalGradientDescent <T> create ( Scope scope, Operand <T> var, Operand <T> alpha, Operand <T> l1, Operand <T> l2, Operand <T> grad, Operand <? extends TNumber > indices, Options... options)

Factory method to create a class wrapping a new SparseApplyProximalGradientDescent 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.
grad The gradient.
indices A vector of indices into the first dimension of var and accum.
options carries optional attributes values
Returns
  • a new instance of SparseApplyProximalGradientDescent

public Output <T> out ()

Same as "var".

public static SparseApplyProximalGradientDescent.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.