ApplyProximalAdagrad

public final class ApplyProximalAdagrad

Update '*var' and '*accum' according to FOBOS with Adagrad learning rate.

accum += grad grad prox_v = var - lr grad (1 / sqrt(accum)) var = sign(prox_v)/(1+lr l2) max{|prox_v|-lr l1,0}

Nested Classes

class ApplyProximalAdagrad.Options Optional attributes for ApplyProximalAdagrad

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

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 ApplyProximalAdagrad <T> create ( Scope scope, Operand <T> var, Operand <T> accum, Operand <T> lr, Operand <T> l1, Operand <T> l2, Operand <T> grad, Options... options)

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

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

public Output <T> out ()

Same as "var".

public static ApplyProximalAdagrad.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.