mxnet.optimizer.adamax

Adamax optimizer.

Classes

Adamax([learning_rate, beta1, beta2, ...])

The AdaMax optimizer.
class mxnet.optimizer.adamax.Adamax(learning_rate=0.002, beta1=0.9, beta2=0.999, epsilon=1e-08, use_fused_step=False, **kwargs)[source]

Bases: Optimizer

The AdaMax optimizer.

It is a variant of Adam based on the infinity norm available at http://arxiv.org/abs/1412.6980 Section 7.

The optimizer updates the weight by:

grad = clip(grad * rescale_grad, clip_gradient) + wd * weight
m = beta1 * m_t + (1 - beta1) * grad
u = maximum(beta2 * u, abs(grad))
weight -= lr / (1 - beta1**t) * m / (u + epsilon)

This optimizer accepts the following parameters in addition to those accepted by Optimizer.

Parameters:

  • learning_rate (float, default 0.002) – The initial learning rate. If None, the optimization will use the learning rate from lr_scheduler. If not None, it will overwrite the learning rate in lr_scheduler. If None and lr_scheduler is also None, then it will be set to 0.01 by default.

  • beta1 (float, default 0.9) – Exponential decay rate for the first moment estimates.

  • beta2 (float, default 0.999) – Exponential decay rate for the second moment estimates.

  • use_fused_step (bool, default False) – Whether or not to use fused kernels for optimizer. When use_fused_step=False, step is called, otherwise, fused_step is called.

create_state(index, weight)[source]

Creates auxiliary state for a given weight.

Some optimizers require additional states, e.g. as momentum, in addition to gradients in order to update weights. This function creates state for a given weight which will be used in update. This function is called only once for each weight.

Parameters:

  • index (int) – An unique index to identify the weight.

  • weight (NDArray) – The weight.

Returns:

state – The state associated with the weight.

Return type:

any obj

step(indices, weights, grads, states)[source]

Perform an optimization step using gradients and states.

Parameters:

  • indices (list of int) – List of unique indices of the parameters into the individual learning rates and weight decays. Learning rates and weight decay may be set via set_lr_mult() and set_wd_mult(), respectively.

  • weights (list of NDArray) – List of parameters to be updated.

  • grads (list of NDArray) – List of gradients of the objective with respect to this parameter.

  • states (List of any obj) – List of state returned by create_state().