mx.symbol.multi_mp_sgd_mom_update

Description

Momentum update function for multi-precision Stochastic Gradient Descent (SGD) optimizer.

Momentum update has better convergence rates on neural networks. Mathematically it looks like below:

\[\begin{split}v_1 = \alpha * \nabla J(W_0)\\ v_t = \gamma v_{t-1} - \alpha * \nabla J(W_{t-1})\\ W_t = W_{t-1} + v_t\end{split}\]

It updates the weights using:

v = momentum * v - learning_rate * gradient
weight += v

Where the parameter ``momentum`` is the decay rate of momentum estimates at each epoch.

Usage

mx.symbol.multi_mp_sgd_mom_update(...)

Arguments

Argument

Description

data

NDArray-or-Symbol[].

Weights

lrs

tuple of <float>, required.

Learning rates.

wds

tuple of <float>, required.

Weight decay augments the objective function with a regularization term that penalizes large weights. The penalty scales with the square of the magnitude of each weight.

momentum

float, optional, default=0.

The decay rate of momentum estimates at each epoch.

rescale.grad

float, optional, default=1.

Rescale gradient to grad = rescale_grad*grad.

clip.gradient

float, optional, default=-1.

Clip gradient to the range of [-clip_gradient, clip_gradient] If clip_gradient <= 0, gradient clipping is turned off. grad = max(min(grad, clip_gradient), -clip_gradient).

num.weights

int, optional, default=’1’.

Number of updated weights.

name

string, optional.

Name of the resulting symbol.