Update relevant entries in '*var' according to the Ftrl-proximal scheme.
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
Nested Classes
class | ResourceSparseApplyFtrl.Options | Optional attributes for ResourceSparseApplyFtrl
|
Constants
String | OP_NAME | The name of this op, as known by TensorFlow core engine |
Public Methods
static <T extends TType> ResourceSparseApplyFtrl |
create(Scope scope, Operand<?> var, Operand<?> accum, Operand<?> linear, Operand<T> grad, Operand<? extends TNumber> indices, Operand<T> lr, Operand<T> l1, Operand<T> l2, Operand<T> l2Shrinkage, Operand<T> lrPower, Options... options)
Factory method to create a class wrapping a new ResourceSparseApplyFtrl operation.
|
static ResourceSparseApplyFtrl.Options |
multiplyLinearByLr(Boolean multiplyLinearByLr)
|
static ResourceSparseApplyFtrl.Options |
useLocking(Boolean useLocking)
|
Inherited Methods
Constants
public static final String OP_NAME
The name of this op, as known by TensorFlow core engine
Public Methods
public static ResourceSparseApplyFtrl create (Scope scope, Operand<?> var, Operand<?> accum, Operand<?> linear, Operand<T> grad, Operand<? extends TNumber> indices, Operand<T> lr, Operand<T> l1, Operand<T> l2, Operand<T> l2Shrinkage, Operand<T> lrPower, Options... options)
Factory method to create a class wrapping a new ResourceSparseApplyFtrl operation.
Parameters
scope | current scope |
---|---|
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 shrinkage regularization. Must be a scalar. |
lrPower | Scaling factor. Must be a scalar. |
options | carries optional attributes values |
Returns
- a new instance of ResourceSparseApplyFtrl
public static ResourceSparseApplyFtrl.Options useLocking (Boolean useLocking)
Parameters
useLocking | 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. |
---|