tensorflow::ops::SparseApplyProximalGradientDescent

#include <training_ops.h>

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

Summary

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}

Arguments:

• scope: A Scope object
• 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.

Optional attributes (see Attrs):

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

Returns:

• Output: Same as "var".

Public attributes

::tensorflow::Output out

Public functions

 SparseApplyProximalGradientDescent(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input alpha,
  ::tensorflow::Input l1,
  ::tensorflow::Input l2,
  ::tensorflow::Input grad,
  ::tensorflow::Input indices
)

 SparseApplyProximalGradientDescent(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input alpha,
  ::tensorflow::Input l1,
  ::tensorflow::Input l2,
  ::tensorflow::Input grad,
  ::tensorflow::Input indices,
  const SparseApplyProximalGradientDescent::Attrs & attrs
)

::tensorflow::Node * node() const 

operator::tensorflow::Input() const 

operator::tensorflow::Output() const 

Public static functions

Attrs UseLocking(
  bool x
)