-
Hi all and thanks for the this very useful package ! It could be helpful to get in addition to the islipschitzcont attribute, another attribute that gives the value of the global Lipschitz constant, e…
-
Hello,
Thank you for sharing this codebase! Is it possible to estimate the Lipschitz constant of the proposed network and its components? (specifically including the self-attention mechanism)
-
The function `evaluate_lip_const` in the `deel.lip.utils` module use a sampled method. Although this is acceptable in a low dimensional space (as done in tests) the measured constant can be heavily un…
-
In the [FGP_TV](https://github.com/vais-ral/CCPi-Regularisation-Toolkit/blob/master/src/Core/regularisers_CPU/FGP_TV_core.c#L241) class for the CCPi-Regularisation Toolkit the step-size (Lipschitz con…
-
@juancprzs
I studied your paper and code carefully. I have a question. Which part of the code in `gabor_layers.py` reflects Lipschitz Constant Regularization?
![222](https://user-images.githubuserc…
-
Hello,
With this repo, is there an easy way to get the local Lipschitz constant of a customized Pytorch CNN on a given image, using the RecurJac method? Thanks.
-
Currently, we are approximating the Lipschitz constant as in scikit-learn by using the maximum absolute rowise squared norm, whilst the theoretically best choice, if I am not mistaken, is to take the …
-
For a differentiable function that is Lipschitz continuous with constant L, give a bound on the derivative (for functions mapping R to R). (Write down the limit form of the derivative -- each quotien…
-
### 🐛 Describe the bug
I would like to raise a concern about the spectral_norm parameterization.
I strongly believe that Spectral-Normalization Parameterization introduced several versions ago do…
-
## Description
Add upper bounds for Lipschitz constants / precision of calculations, return those estimates.