-
Look into whether this would be a good addition
-
Nice implementation! I notice a small detour below and wonder if it's necessary:
In this [line](https://github.com/johnma2006/mamba-minimal/blob/03de542a36d873f6e6c4057ad687278cc6ae944d/model.py#L201…
-
AutoEnzyme should probably be specialized and not fall back to DI.
In addition to being slower in some cases, it's been shown to cause errors (even segfaults) when using AutoEnzyme in DI whereas us…
-
Hello,
Thanks you for sharing your code. I am looking at line 193, in plot_learning_dynamics.py. I want to know how to extract the train accuracy and test accuracy of the mean GP-FNN predictor acro…
-
Union types express a subtyping relationship, but I am unclear as to whether typeclasses (i.e. Rust's traits) do?
If a `trait B` extends another `trait A` and `B` reuses the implementations of `A`, c…
-
This is a great library first of all, so kudos to the developers !
My questions is: In the Package description in section `predict.gradient_descent_mse_ensemble` and you mention a paper as [11] but …
-
First, thank you for this handy library.
I have a question about ``stax.Aggregate`` function.
I tried to use ``neural_tangents.predict`` library with graph neural tangent kernel (i.e.``stax.aggrega…
-
Hi, I'm really impressed by your insightful work.
I have a few questions:
1. Although networks with ReLU activations are not shift-invariant, I think deep networks with BatchNrom or LayerNorm a…
-
Hi, I'm new to neural tangents. I don't quite understand the output dimensions in the examples.
As my understanding, the kernel size calculated by `kernel_fn` should be `N*N`, and the example for …
-
https://www.usenix.org/system/files/conference/osdi14/osdi14-paper-chilimbi.pdf