tensorflow:: ops:: ResourceApplyProximalGradientDescent

#include <training_ops.h>

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}

Args:

  • 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 (see Attrs ):

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

Returns:

Constructors and Destructors

ResourceApplyProximalGradientDescent (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input alpha, :: tensorflow::Input l1, :: tensorflow::Input l2, :: tensorflow::Input delta)
ResourceApplyProximalGradientDescent (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input alpha, :: tensorflow::Input l1, :: tensorflow::Input l2, :: tensorflow::Input delta, const ResourceApplyProximalGradientDescent::Attrs & attrs)

Public attributes

operation

Public functions

operator::tensorflow::Operation () const

Public static functions

UseLocking (bool x)

Structs

tensorflow:: ops:: ResourceApplyProximalGradientDescent:: Attrs

Optional attribute setters for ResourceApplyProximalGradientDescent .

Public attributes

operation 

Operation operation

Public functions

ResourceApplyProximalGradientDescent 

 ResourceApplyProximalGradientDescent(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input alpha,
  ::tensorflow::Input l1,
  ::tensorflow::Input l2,
  ::tensorflow::Input delta
)

ResourceApplyProximalGradientDescent 

 ResourceApplyProximalGradientDescent(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input alpha,
  ::tensorflow::Input l1,
  ::tensorflow::Input l2,
  ::tensorflow::Input delta,
  const ResourceApplyProximalGradientDescent::Attrs & attrs
)

operator::tensorflow::Operation 

 operator::tensorflow::Operation() const

Public static functions

UseLocking 

Attrs UseLocking(
  bool x
)