Jesse Grabowski

Let's do it, what needs to happen?

Yes

This issue made me think of this paper: https://arxiv.org/abs/2302.00564 But maybe this is thinking about fully conjugate models, not intermediate relationships?

Are pushforward and pullback widely used in the auto-diff literature? I've personally not seen them before, and [this paper](https://arxiv.org/pdf/2002.08241v1.pdf), explicitly distinguishes between them. It seems to me that names like...

cc @ferrine

cc: @Armavica @maresb

This is OK for me. The convention would be `name_var`. You will need something in the `__init__` method of the different models (BayesianSARIMAX, VARMAX, ETS, DFM), but also in the...

Can you post some timings showing that this is advantageous? `inv(A)` and `solve(A, Eye)` are basically the same thing. I recognize that there is some advantage because you're using the...

That's really awesome! Thanks for doing this study. Given these results, my suggestion would be to make a `TriangularInv` `Op` that subclasses from `Inv`. In the perform method, use `trtri`...

> Also, if helpful, I can start a separate issue to track TriangularInv(x) @ b. Sure, feel free to open an issue. If you prefer to wait for this to...