Sparse update '*var' as FOBOS algorithm with fixed learning rate.
tf.raw_ops.SparseApplyProximalGradientDescent(
var, alpha, l1, l2, grad, indices, use_locking=False, name=None
)
That is for rows we have grad for, we update var as follows:
\[prox_v = var - alpha * grad\]
\[var = sign(prox_v)/(1+alpha*l2) * max{|prox_v|-alpha*l1,0}\]
Args |
|---|
var
|
A mutable Tensor. Must be one of the following types: float32, float64, int32, uint8, int16, int8, complex64, int64, qint8, quint8, qint32, bfloat16, qint16, quint16, uint16, complex128, half, uint32, uint64.
Should be from a Variable().
|
alpha
|
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.
|
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.
|
use_locking
|
An optional bool. Defaults to False.
If True, the subtraction 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.
|
