-
This could be implemented in a similar way to [`DifferentiateWith`](https://github.com/gdalle/DifferentiationInterface.jl/blob/8077dce045055f76b28adc67c334dbb62ce79a3e/DifferentiationInterface/src/mis…
-
Hi there,
Thank you for all your work! I have seen that recently, pull request https://github.com/JuliaStats/StatsFuns.jl/pull/147 was closed in favor of https://github.com/JuliaStats/StatsFuns.jl…
-
Zygote now depends also on ChainRulesCore in addition to ChainRules. Should we add it to the integration tests?
-
Related to https://github.com/JuliaDiff/FiniteDifferences.jl/issues/52, it seems there is currently no way to specify constraints on function arguments to FiniteDifferences. For instance, when testing…
-
Hello,
I have been for educational purposes implementing RNN by hand and wanted to be fancy and use `accumulate` instead of recursion or for rule. But I run into an error, when one of the operands …
-
Here is the example:
```julia
using TensorKit, Zygote
g(x)=real(scalar(x'*x))
V=Z3Space(0=>2,1=>2,2=>2);
A=randn(ComplexF64,V*V*V',one(V));
gradient(g,A)
```
Output:
```
ERROR: MethodError…
-
Hi, it seems that the `rrule` for `mean(f, x)` is not vectorized and thus does not place nicely with CUDA:
```julia
using Zygote, CUDA, Statistics
julia> gradient(y -> mean(x -> x.^2, y), CUDA.…
-
Some rules use scalar indexing, breaking GPU compatibility, e.g., https://github.com/JuliaDiff/ChainRules.jl/blob/3b3791f10bc88c41f004fbb9eb229745d1764593/src/rulesets/LinearAlgebra/norm.jl#L187
On…
-
Integers can't be perturbed, so their `to_vec` should be empty. Originally suggested in https://github.com/JuliaDiff/FiniteDifferences.jl/pull/187
```julia
function to_vec(x::Integer)
Integer_…
-
It seems annoying that the pushforward and pullback function accept tuples of co-tangents instead of multiple arguments. Is there a compelling reason for doing so or was this a design decision that co…