tf.raw_ops.ApplyPowerSign

Update '*var' according to the AddSign update.

tf.raw_ops.ApplyPowerSign(
    var, m, lr, logbase, sign_decay, beta, grad, use_locking=False, name=None
)

mt <- beta1 * m{t-1} + (1 - beta1) * g update <- exp(logbase * sign_decay * sign(g) * sign(m_t)) * g variable <- variable - lr_t * update

Args:

  • var: A mutable Tensor. Must be one of the following types: float32, float64, int32, uint8, int16, int8, complex64, int64, qint8, quint8, qint32, bfloat16, uint16, complex128, half, uint32, uint64. Should be from a Variable().
  • m: A mutable Tensor. Must have the same type as var. Should be from a Variable().
  • lr: A Tensor. Must have the same type as var. Scaling factor. Must be a scalar.
  • logbase: A Tensor. Must have the same type as var. Must be a scalar.
  • sign_decay: A Tensor. Must have the same type as var. Must be a scalar.
  • beta: A Tensor. Must have the same type as var. Must be a scalar.
  • grad: A Tensor. Must have the same type as var. The gradient.
  • use_locking: An optional bool. Defaults to False. If True, updating of the var and m tensors is protected by a lock; otherwise the behavior is undefined, but may exhibit less contention.
  • name: A name for the operation (optional).

Returns:

A mutable Tensor. Has the same type as var.