tf.raw_ops.ResourceSparseApplyFtrlV2

Stay organized with collections Save and categorize content based on your preferences.

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

View aliases

Compat aliases for migration

tf.compat.v1.raw_ops.ResourceSparseApplyFtrlV2

tf.raw_ops.ResourceSparseApplyFtrlV2(
    var,
    accum,
    linear,
    grad,
    indices,
    lr,
    l1,
    l2,
    l2_shrinkage,
    lr_power,
    use_locking=False,
    multiply_linear_by_lr=False,
    name=None
)

That is for rows we have grad for, we update var, accum and linear as follows: grad_with_shrinkage = grad + 2 * l2_shrinkage * var accum_new = accum + grad_with_shrinkage * grad_with_shrinkage linear += grad_with_shrinkage + (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 Tensor of type resource. Should be from a Variable().
accum	A Tensor of type resource. Should be from a Variable().
linear	A Tensor of type resource. Should be from a Variable().
grad	A 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. 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 grad. Scaling factor. Must be a scalar.
l1	A Tensor. Must have the same type as grad. L1 regularization. Must be a scalar.
l2	A Tensor. Must have the same type as grad. L2 shrinkage regularization. Must be a scalar.
l2_shrinkage	A Tensor. Must have the same type as grad.
lr_power	A Tensor. Must have the same type as grad. 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).

Returns
The created Operation.

tf.raw_ops.ResourceSparseApplyFtrlV2 | TensorFlow v2.16.1 (original) (raw)

View aliases