climin
climin copied to clipboard
BRML
Optimizers for machine learning
Useful for implementing gradient projection type algorithms on the probability simplex.
Optimization schemes with complex numbers are widely used in physics, and recently, machine learning. I strongly suggest to add the support to complex numbers for optimization engines like **RmsProp** et....
The bfgs object does not have a logfunc attribute or method
Contrary to what the docstring says, gradient descent does not accept a sequence for the `step_rate` parameter. I'm happy to submit a pull request for this, if there's still interest!
Hi, I'd love to see this package in PyPI. Any plans to do so? It would help installing the package and declaring it as a dependency. Just to reserve the...
I think in the original paper of adadelta, there is no step_rate.
@bayerj The `152-th` line of `rmsprop.py` ``` self.moving_mean_squared = 1 ``` I think the initial value should be `0` instead of `1`. Any reason why `1` is better than `0`
I'm slightly confused about the final steps described in the doc vs the code below, should the Nesterov momentum be applied before updating the parameters, i.e.: self.wrt -= step1 +...
