ApplyProximalGradientDescent

tensorflow C++ API

tensorflow::ops::ApplyProximalGradientDescent

Update ‘*var’ as FOBOS algorithm with fixed learning rate.

Summary

prox_v = var - alpha * delta var = sign(prox_v)/(1+alpha*l2) * max{|prox_v|-alpha*l1,0}

Arguments:

• scope: A Scope object
• 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.
• delta: The change.

Optional attributes (seeAttrs):

• use_locking: If True, the subtraction will be protected by a lock; otherwise the behavior is undefined, but may exhibit less contention.

Returns:

• Output: Same as “var”.

ApplyProximalGradientDescent block

Source link : https://github.com/EXPNUNI/enuSpaceTensorflow/blob/master/enuSpaceTensorflow/tf_training.cpp

Argument:

• Scope scope : A Scope object (A scope is generated automatically each page. A scope is not connected.)
• Input var: connect Input node.
• Input alpha: connect Input node.
• Input l1: connect Input node.
• Input l2: connect Input node.
• Input delta: connect Input node.
• ApplyProximalGradientDescent ::Attrs attrs : Input attrs in value. ex) use_locking_ = false;

Return:

• Output output : Output object of ApplyProximalGradientDescent class object.

Result:

• std::vector(Tensor) result_output : Returned object of executed result by calling session.

Using Method