Yes, precisely. It gets complicated very quickly. Cotangents for structural matrices in reverse-mode AD tend to wander away from the cotangent space at the corresponding point into the tangent space of the embedding for…
or that the tooling for the problems I do have is adequate in multiple languages.
My point is I think simpler than what you're talking about, so let's replace "symmetric" with "diagonal." Suppose I have a structurally diagonal matrix, represented by a type `Diagonal` that can only represent diagonal…
Statistics is usually considered a subset of ML, except maybe by statisticians. While R definitely leads the pack on variety of useful stats packages, there are excellent tools for certain tasks in other languages. I do…
I'd be interested to know whether that occurred pre- or post- Zygote.jl starting to use ChainRules.jl internally. Zygote's own rules used to be tested with a half-baked finite differences scheme, and it was easy to miss…
Yes, precisely. It gets complicated very quickly. Cotangents for structural matrices in reverse-mode AD tend to wander away from the cotangent space at the corresponding point into the tangent space of the embedding for…
or that the tooling for the problems I do have is adequate in multiple languages.
My point is I think simpler than what you're talking about, so let's replace "symmetric" with "diagonal." Suppose I have a structurally diagonal matrix, represented by a type `Diagonal` that can only represent diagonal…
Statistics is usually considered a subset of ML, except maybe by statisticians. While R definitely leads the pack on variety of useful stats packages, there are excellent tools for certain tasks in other languages. I do…
I'd be interested to know whether that occurred pre- or post- Zygote.jl starting to use ChainRules.jl internally. Zygote's own rules used to be tested with a half-baked finite differences scheme, and it was easy to miss…