tensorflow::
ops::
SparseApplyProximalAdagrad
#include <training_ops.h>
Sparse update entries in '*var' and '*accum' according to FOBOS algorithm.
Summary
That is for rows we have grad for, we update var and accum as follows:
$$accum += grad * grad$$
$$prox_v = var$$
$$prox_v -= lr * grad * (1 / sqrt(accum))$$
$$var = sign(prox_v)/(1+lr*l2) * max{|prox_v|-lr*l1,0}$$
Args:
- scope: A Scope object
- var: Should be from a Variable().
- accum: Should be from a Variable().
- lr: Learning rate. 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.
Optional attributes (see
Attrs
):
- use_locking: 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.
Returns:
-
Output
: Same as "var".
Constructors and Destructors |
|
---|---|
SparseApplyProximalAdagrad
(const ::
tensorflow::Scope
& scope, ::
tensorflow::Input
var, ::
tensorflow::Input
accum, ::
tensorflow::Input
lr, ::
tensorflow::Input
l1, ::
tensorflow::Input
l2, ::
tensorflow::Input
grad, ::
tensorflow::Input
indices)
|
|
SparseApplyProximalAdagrad
(const ::
tensorflow::Scope
& scope, ::
tensorflow::Input
var, ::
tensorflow::Input
accum, ::
tensorflow::Input
lr, ::
tensorflow::Input
l1, ::
tensorflow::Input
l2, ::
tensorflow::Input
grad, ::
tensorflow::Input
indices, const
SparseApplyProximalAdagrad::Attrs
& attrs)
|
Public attributes |
|
---|---|
operation
|
|
out
|
Public functions |
|
---|---|
node
() const
|
::tensorflow::Node *
|
operator::tensorflow::Input
() const
|
|
operator::tensorflow::Output
() const
|
|
Public static functions |
|
---|---|
UseLocking
(bool x)
|
Structs |
|
---|---|
tensorflow::
|
Optional attribute setters for SparseApplyProximalAdagrad . |
Public attributes
Public functions
SparseApplyProximalAdagrad
SparseApplyProximalAdagrad( const ::tensorflow::Scope & scope, ::tensorflow::Input var, ::tensorflow::Input accum, ::tensorflow::Input lr, ::tensorflow::Input l1, ::tensorflow::Input l2, ::tensorflow::Input grad, ::tensorflow::Input indices )
SparseApplyProximalAdagrad
SparseApplyProximalAdagrad( const ::tensorflow::Scope & scope, ::tensorflow::Input var, ::tensorflow::Input accum, ::tensorflow::Input lr, ::tensorflow::Input l1, ::tensorflow::Input l2, ::tensorflow::Input grad, ::tensorflow::Input indices, const SparseApplyProximalAdagrad::Attrs & attrs )
node
::tensorflow::Node * node() const
operator::tensorflow::Input
operator::tensorflow::Input() const
operator::tensorflow::Output
operator::tensorflow::Output() const