tf.raw_ops.SparseApplyFtrl

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

tf.raw_ops.SparseApplyFtrl(
    var, accum, linear, grad, indices, lr, l1, l2, lr_power, use_locking=False,
    name=None
)

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

\(accum_new = accum + grad * grad\)
\(linear += grad + (accum_{new}^{-lr_{power} } - accum^{-lr_{power} } / lr * var\)
\(quadratic = 1.0 / (accum_{new}^{lr_{power} } * lr) + 2 * l2\)
\(var = (sign(linear) * l1 - linear) / quadratic\ if\ |linear| > l1\ else\ 0.0\)
\(accum = accum_{new}\)

Args:

  • var: A mutable Tensor. Must be one of the following types: float32, float64, int32, uint8, int16, int8, complex64, int64, qint8, quint8, qint32, bfloat16, uint16, complex128, half, uint32, uint64. Should be from a Variable().
  • accum: A mutable Tensor. Must have the same type as var. Should be from a Variable().
  • linear: A mutable Tensor. Must have the same type as var. Should be from a Variable().
  • grad: A Tensor. Must have the same type as var. The gradient.
  • indices: A Tensor. Must be one of the following types: int32, int64. A vector of indices into the first dimension of var and accum.
  • lr: A Tensor. Must have the same type as var. Scaling factor. Must be a scalar.
  • l1: A Tensor. Must have the same type as var. L1 regularization. Must be a scalar.
  • l2: A Tensor. Must have the same type as var. L2 regularization. Must be a scalar.
  • lr_power: A Tensor. Must have the same type as var. Scaling factor. Must be a scalar.
  • use_locking: An optional bool. Defaults to False. 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.
  • name: A name for the operation (optional).

Returns:

A mutable Tensor. Has the same type as var.