-
Hi @fredo-dedup, I hope all is well with you. As you will see, I updated Lora after pushing the work of the last 9 months. I want to now re-enable autodiff in our Lora package using your ReverseDiffSo…
-
Hi!
So tangent worked great in my demo, but now that I'm starting to hit it with more complicated functions it's giving mysterious errors...
If someone can point me at what's going wrong here, I…
-
Hi all !
I was wondering, why did you choose to use chunk-wise forward AD, and not use http://www.juliadiff.org ?
Best,
Emile
-
Hi,
the following code produces the subsequent error:
`tangent_df = tangent.grad(fun, verbose = 1, mode='forward')`
```
Traceback (most recent call last):
File "autoDiff.py", line 114, in…
-
## 🐛 Bug
PyTorch fails to finish building, with a possible bug (see below).
```bash
Scanning dependencies of target caffe2_observers
[ 92%] Building CXX object caffe2/torch/lib/THD/CMakeFiles…
-
#### Summary:
Add a `logistic_regression` function with analytic gradients that behaves as if defined (up in the Stan language) by:
```
real logistic_regression(int[] y, matrix x, vector beta, …
-
DiffEqDiffTools supports much faster finite differencing routines than Calculus.
Ref: discussion on gitter.
-
## 🐛 Bug
Torch fails to build (even with `BUILD_TEST=0`) on `/opt/pytorch/torch/csrc/Dtype.cpp`; looks like another instance of warning converted to errors:
```bash
[0mFirst, rewinding head to…
-
Sometimes gradients are vectorized, and sometimes they are not. Consider this example where the gradient is vectorized (ie. array in, array of derivatives out).
```
def f(x):
return x**2
d…
-
Hamiltonian Monte Carlo (HMC), also known as Hybrid Monte Carlo, is an efficient Markov Chain Monte Carlo (MCMC) method that exploits gradient information to improve on the simpler MCMC methods. See t…