public final class
ResourceSparseApplyProximalGradientDescent
Sparse update '*var' as FOBOS algorithm with fixed learning rate.
That is for rows we have grad for, we update var as follows: prox_v = var - alpha grad var = sign(prox_v)/(1+alphal2) max{|prox_v|-alphal1,0}
Nested Classes
class | ResourceSparseApplyProximalGradientDescent.Options | Optional attributes for ResourceSparseApplyProximalGradientDescent
|
Constants
String | OP_NAME | The name of this op, as known by TensorFlow core engine |
Public Methods
static <T extends TType> ResourceSparseApplyProximalGradientDescent | |
static ResourceSparseApplyProximalGradientDescent.Options |
useLocking(Boolean useLocking)
|
Inherited Methods
Constants
public static final String OP_NAME
The name of this op, as known by TensorFlow core engine
Constant Value:
"ResourceSparseApplyProximalGradientDescent"
Public Methods
public static ResourceSparseApplyProximalGradientDescent create (Scope scope, Operand<?> var, Operand<T> alpha, Operand<T> l1, Operand<T> l2, Operand<T> grad, Operand<? extends TNumber> indices, Options... options)
Factory method to create a class wrapping a new ResourceSparseApplyProximalGradientDescent operation.
Parameters
scope | current scope |
---|---|
var | Should be from a Variable(). |
alpha | Scaling factor. Must be a scalar. |
l1 | L1 regularization. Must be a scalar. |
l2 | L2 regularization. Must be a scalar. |
grad | The gradient. |
indices | A vector of indices into the first dimension of var and accum. |
options | carries optional attributes values |
Returns
- a new instance of ResourceSparseApplyProximalGradientDescent
public static ResourceSparseApplyProximalGradientDescent.Options useLocking (Boolean useLocking)
Parameters
useLocking | If True, the subtraction will be protected by a lock; otherwise the behavior is undefined, but may exhibit less contention. |
---|