-
### Describe the workflow you want to enable
Similarly to what is mentioned on https://github.com/scikit-learn/scikit-learn/issues/9273
> Training an MLP regressor (or classifier) using l-bfgs cur…
-
Hi,
Is there any way to retrieve the `hess_inv` (approximated inverse Hessian) after running the BFGS optimizer? In the original scipy's implementation, the matrix is stored in the return `OptimizeRe…
-
#### Issue description
Following the example.cpp, I was playing around with some callbacks functions. For example, I realized if I use the Adam optimizer, the callback function ProgressBar() works …
-
Hi,
I tried to train the model with L-BFGS after 15000 iterations of Adam, but I got different results from tensorflow.compat.v1 and PyTorch, even if I use the exact same code, just a different bac…
-
First of all thank you for sharing your implementation of l-bfgs-b. I have faced an issue I hope you can help me with. During optimization, I constantly get the warning" negative curvature detected, …
-
As is stated in #419, `BFGS` and `adaptive` each have cases that they cannot resolve, which could be resolved by the other estimator.
I'm thinking of adding a more robust solver in the downstream pac…
-
Is there an agenda for implementing bounded optimization method like L-BFGS-B?
Scipy already has a functional method here scipy.optimize.fmin_l_bfgs_b.
-
Editing the neural_style_transfer.py and changing the default value for --height or using --height value on the command line produces no end result. The data/output-images folder created is blank.
…
-
I've been working on a Navier Stokes problem and would like to try to further optimize my model after training with Adam like many of the examples I have seen. However, when trying to use this optimiz…
-