-
## Description
The ODE functors aren't compatible with `fvar` inputs and fail to compile
#### Current Version:
v4.4.0
-
```python
def test():
x = []
for i in range(5):
x.append(i)
return x
```
```pytb
In [10]: xxx = tangent.grad(test)
--------------------------------------------------------…
-
Hi Jax team,
We want to calculate hessians of a likelihood function involving an ode integration so that we can do variational inference. We are running into an issue with `custom_vjp`, which we do…
-
A typical optimization process is evaluating usually the same derivatives at different points. Right now, the derivative is calculated from scratch each time (40sec in my case, where it should be less…
-
Hi,
Unfortunately, all the available (S)ODE integration subroutines in auto-differentiable Python frameworks (RK45, Dopri, etc.) behave very poorly with complex-valued functions [*]. In the Python …
-
One of the nice things about the new autodiff system is that it incorporates operands and partials directly, which will make implementing functions and implementing distributions identical.
An immedi…
-
Hi,
I have an optimization problem where my cost function _f_ depends on _n_ (usually >100) input variables (vector **FA**) and also a handful of vector parameters with the same size:
~~~c++
va…
-
Hi, I was wondering if this project is still under development or abandoned. I have quite a few issues which I don't know if I should bother posting here. So, sorry for the issue spam if there is no i…
-
OK, so this is pretty speculative as the reverse differentiation packages are not there yet, but let's dream for a moment. It would be awesome to be able to just use reverse-mode differentiation on co…
-
Currently in my experiments with `differential(at: p, in: f)` the following error is thrown:
```
Fatal error: JVP does not exist. Differential-first differentiation APIs are experimental and should …