tf.raw_ops.SparseApplyFtrl

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

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.raw_ops.SparseApplyFtrl

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

accumnew=accum+gradgrad

linear+=grad+(accumnewlrpoweraccumlrpower/lrvar

quadratic=1.0/(accumnewlrpowerlr)+2l2

var=(sign(linear)l1linear)/quadratic if |linear|>l1 else 0.0

accum=accumnew

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.
multiply_linear_by_lr An optional bool. Defaults to False.
name A name for the operation (optional).

A mutable Tensor. Has the same type as var.