mxnet.optimizer.Signum¶

class mxnet.optimizer.Signum(learning_rate=0.01, momentum=0.9, wd_lh=0.0, **kwargs)[source]¶

The Signum optimizer that takes the sign of gradient or momentum.

The optimizer updates the weight by:

rescaled_grad = rescale_grad * clip(grad, clip_gradient) + wd * weight
state = momentum * state + (1-momentum)*rescaled_grad
weight = (1 - lr * wd_lh) * weight - lr * sign(state)

References

Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli & Anima Anandkumar. (2018). signSGD: Compressed Optimisation for Non-Convex Problems. In ICML‘18.

See: https://arxiv.org/abs/1802.04434

For details of the update algorithm see signsgd_update and signum_update.

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

Parameters

momentum (float, optional) – The momentum value.
wd_lh (float, optional) – The amount of decoupled weight decay regularization, see details in the original paper at:https://arxiv.org/abs/1711.05101

__init__(learning_rate=0.01, momentum=0.9, wd_lh=0.0, **kwargs)[source]¶: Initialize self. See help(type(self)) for accurate signature.

Methods

`__init__`([learning_rate, momentum, wd_lh])	Initialize self.
`create_optimizer`(name, **kwargs)	Instantiates an optimizer with a given name and kwargs.
`create_state`(index, weight)	Creates auxiliary state for a given weight.
`create_state_multi_precision`(index, weight)	Creates auxiliary state for a given weight, including FP32 high precision copy if original weight is FP16.
`register`(klass)	Registers a new optimizer.
`set_learning_rate`(lr)	Sets a new learning rate of the optimizer.
`set_lr_mult`(args_lr_mult)	Sets an individual learning rate multiplier for each parameter.
`set_lr_scale`(args_lrscale)	[DEPRECATED] Sets lr scale.
`set_wd_mult`(args_wd_mult)	Sets an individual weight decay multiplier for each parameter.
`update`(index, weight, grad, state)	Updates the given parameter using the corresponding gradient and state.
`update_multi_precision`(index, weight, grad, …)	Updates the given parameter using the corresponding gradient and state.

Attributes

`learning_rate`
`opt_registry`