tensorflow::ops::SparseApplyFtrl

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

Summary

That is for rows we have grad for, we update var, accum and linear as follows: $$accum_new = accum + grad * grad$$ $$linear += grad + (accum_{new}^{-lr_{power}} - accum^{-lr_{power}} / lr * var$$ $$quadratic = 1.0 / (accum_{new}^{lr_{power}} * lr) + 2 * l2$$ $$var = (sign(linear) * l1 - linear) / quadratic\ if\ |linear| > l1\ else\ 0.0$$ $$accum = accum_{new}$$

Arguments:

• scope: A Scope object
• var: Should be from a Variable().
• accum: Should be from a Variable().
• linear: Should be from a Variable().
• grad: The gradient.
• indices: A vector of indices into the first dimension of var and accum.
• lr: Scaling factor. Must be a scalar.
• l1: L1 regularization. Must be a scalar.
• l2: L2 regularization. Must be a scalar.
• lr_power: Scaling factor. Must be a scalar.

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".

Public attributes

Operation operation

::tensorflow::Output out

 SparseApplyFtrl(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input accum,
  ::tensorflow::Input linear,
  ::tensorflow::Input grad,
  ::tensorflow::Input indices,
  ::tensorflow::Input lr,
  ::tensorflow::Input l1,
  ::tensorflow::Input l2,
  ::tensorflow::Input lr_power
)

 SparseApplyFtrl(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input accum,
  ::tensorflow::Input linear,
  ::tensorflow::Input grad,
  ::tensorflow::Input indices,
  ::tensorflow::Input lr,
  ::tensorflow::Input l1,
  ::tensorflow::Input l2,
  ::tensorflow::Input lr_power,
  const SparseApplyFtrl::Attrs & attrs
)

::tensorflow::Node * node() const 

 operator::tensorflow::Input() const 

 operator::tensorflow::Output() const 

Attrs UseLocking(
  bool x
)