-
I wanted to use split reverse mode in order to compute pullbacks with array outputs. The only doc I found is
so I tried it but it fails on Julia 1.11:
```julia
julia> using Enzyme
julia…
-
### Description
I'm working on a library for numerical quadrature in JAX, with derivatives defined via Leibniz rule. I've defined ``custom_jvp`` for my quadrature functions and it works fine in for…
-
## Description
I was benchmarking determinant and log_determinant today.
For reverse mode for each of these functions you need to evaluate the determinant, and to get the gradients you need the …
-
Hello,
I saw that there is a documented `hessian` driver for the reverse mode. And as I checked through the forward eigen header I found the counterpart. However, I cannot get it to work. My exampl…
-
Is it not sufficient to directly take gradients of U0 w.r.t x?
I think i am missing something here..
much obliged if someone could clear it.
Thanks
-
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…
-
Following our conversation on Slack with @ExpandingMan, just wanted to ask whether the return tuples would be modified or not.
Let's take a function `y = f(x1, x2, x3)` and run `autodiff` on it.
*…
-
I'm writing this issue to capture some of the ideas mentioned in a private discussion with @wsmoses about the future C++ interface. I'm hoping that this will increase visibility and allow other contri…
-
1. [x] discuss the relationship between NiLang and other reversible languages
2. [x] cite and discuss the relation between NiLang and other frameworks utilizing reversibility in ML. Checkpointing. (a…
-
Is it possible to use std::complex as a custom scalar type in reserve mode? Can you add an example?