tf.raw_ops.SparseApplyRMSProp

Update '*var' according to the RMSProp algorithm.

tf.raw_ops.SparseApplyRMSProp(
    var, ms, mom, lr, rho, momentum, epsilon, grad, indices, use_locking=False,
    name=None
)

Note that in dense implementation of this algorithm, ms and mom will update even if the grad is zero, but in this sparse implementation, ms and mom will not update in iterations during which the grad is zero.

mean_square = decay * mean_square + (1-decay) * gradient ** 2 Delta = learning_rate * gradient / sqrt(mean_square + epsilon)

$$ms <- rho * ms_{t-1} + (1-rho) * grad * grad$$
$$mom <- momentum * mom_{t-1} + lr * grad / sqrt(ms + epsilon)$$
$$var <- var - mom$$

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().
  • ms: A mutable Tensor. Must have the same type as var. Should be from a Variable().
  • mom: 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.
  • rho: A Tensor. Must have the same type as var. Decay rate. Must be a scalar.
  • momentum: A Tensor. Must have the same type as var.
  • epsilon: A Tensor. Must have the same type as var. Ridge term. Must be a scalar.
  • grad: A Tensor. Must have the same type as var. The gradient.
  • indices: A Tensor. Must be one of the following types: int32, int64. A vector of indices into the first dimension of var, ms and mom.
  • use_locking: An optional bool. Defaults to False. If True, updating of the var, ms, and mom 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.