# mx.nd.multi.mp.sgd.update¶

## Description¶

Update function for multi-precision Stochastic Gradient Descent (SDG) optimizer.

weight = weight - learning_rate * (gradient + wd * weight)


## 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.

rescale.grad

float, optional, default=1.

clip.gradient

float, optional, default=-1.

num.weights
out The result mx.ndarray