-
So to run moving mesh problems with perfect Jacobians in MOOSE I've developed methods like [`Assembly::computeSinglePointMapAD`](https://github.com/idaholab/moose/blob/next/framework/src/base/Assembly…
-
Since we're capturing the expression graphs, we're in a good position to support automatic differentiation as well. This would require expressions to track a bit more information (the actual arithmet…
-
Supporting reverse-mode autodiff with Zygote requires two things:
- custom pullbacks (reverse-mode differentiation rules, AKA adjoints) for functions that internally mutate arrays (Zygote does not su…
-
Write Doxygen-style documentation for the following topics:
- [ ] Linear algebra
- [ ] Complex numbers
- [ ] Statistics
- [ ] Automatic differentiation
- [ ] Calculus
The existing documentat…
-
Currently, implementations don't support automatic differentiation with packages such as `ForwardDiff.jl`.
Probably best to give ChainRules such as in https://github.com/JuliaMath/SpecialFunctions…
-
A lot of the factors' gradients can be analytically computed. For others, automatic differentiation can be done with packages such as Zygote or ForwardDiff.
I'm starting this broad issue to look at…
Affie updated
2 years ago
-
I've been wondering if there has been any recent progress in integrating `jax` and `xarray`, specifically for automatic differentiation. For context, we have a simulation project that relies on `xarra…
-
Hi there,
Really nice package!
I was wondering if one can adjust the flatten/unflatten functions, such that unflatten is also working inside a closure for using Automatic Differentation.
A…
-
# Automatic differentiation with autograd · Machine-learning
[https://westgrid-ml.netlify.app/schoolremake/pt-13-autograd.html](https://westgrid-ml.netlify.app/schoolremake/pt-13-autograd.html)
-
Please make sure that this is a feature request. As per our [GitHub Policy](https://github.com/tensorflow/tensorflow/blob/master/ISSUES.md), we only address code/doc bugs, performance issues, feature …