You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by GitBox <gi...@apache.org> on 2019/07/23 22:26:00 UTC
[GitHub] [incubator-mxnet] ChaiBapchya opened a new issue #15643: NDArray
API NN Optimizer (Multi-* update category) absent in Doc
ChaiBapchya opened a new issue #15643: NDArray API NN Optimizer (Multi-* update category) absent in Doc
URL: https://github.com/apache/incubator-mxnet/issues/15643
Neural Network Optimizer updates such as
`multi_mp_sgd_mom_update`, `multi_mp_sgd_update`, `multi_sgd_mom_update`, `multi_sgd_update`
They are present in Symbol API doc but not in NDArray API doc.
However, upon checking definition of 1 of the operators
```
>>> help(mx.nd.multi_sgd_mom_update)
```
```
Help on function multi_sgd_mom_update:
multi_sgd_mom_update(*data, **kwargs)
Momentum update function for Stochastic Gradient Descent (SGD) optimizer.
Momentum update has better convergence rates on neural networks. Mathematically it looks
like below:
.. math::
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
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.
Defined in src/operator/optimizer_op.cc:L372
Parameters
----------
data : NDArray[]
Weights, gradients and momentum
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'
```
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services