-
This causes problems with Zygote:
```julia
julia> using Zygote
julia> gradient(x -> sum([x x]), pi/2)
(2.0,)
julia> gradient(x -> sum(Float32[x x]), pi/2)
ERROR: Mutating arrays is not suppo…
-
The sensitivities for `/` and `\` seem to match the definitions for matrix inverse products in the Giles paper, and they work as tested on square matrices. However, the formulas in the paper assume th…
-
MWE
```julia
using Zygote, LinearAlgebra
N = 4
u0 = rand(N)
ps = rand(N)
mats = (rand(N,N), rand(N,N),) # (A, B,)
nums = (rand(), rand(),) # (α, β,)
loss_m = function(p)
v = D…
-
Copied from https://github.com/JuliaMath/SpecialFunctions.jl/pull/305:
> I added ChainRules definitions for gamma(a, x), loggamma(a, x), and gamma_inc according to https://functions.wolfram.com/Gam…
-
```julia
using Zygote, LinearAlgebra
gradient((A,B) -> sum([I A; B I]), randn(2,3), randn(3,2))
```
gives an error.
![image](https://user-images.githubusercontent.com/10637482/145725541-8b369…
-
I would like to suggest a Zygote rrule for the ``StatsBase.jl`` function. I'm not sure whether to post this in the Zygote or in this repo, so please let me know if this is the wrong place.
```julia…
-
e.g. "things should be unthunked before being passed to pullbacks"
- We _show_ this in the ["using ChainRules directly" example](http://www.juliadiff.org/ChainRulesCore.jl/dev/index.html#Example-of-u…
-
I *think* this is a ChainRules.jl problem, not a Diffractor.jl problem but I'm not 100% sure. Here's a MWE:
```julia
julia> using Diffractor: DiffractorForwardBackend; using AbstractDifferentiation:…
-
What kind of structs should we add to enable deep learning applications?
-
This came up in #366.
And it has proved tricky to debug.
AFAICT there were two issues, one from ChainRules directly (I forgot to put the adjoint for `abs(::Complex)` back in, fixed now).
But second…