-
This seems like a really cool project! I was wondering if you'd thought about adding a dimensions system, which would be a nice fit with Lean, since it requires somewhat dependent types.
For exampl…
-
I implemented several linear operators related to solve control problems. An example is the Lyapunov operator L: X -> AX+XA', where A is a squre matrix. This operator acts usually on symmetric/hermiti…
-
## Reason
It is often cumbersome and difficult to derive the gradient for PDE-constrained inverse optimization. It involves developing an adjoint of the forward problem and derivatives with respect…
-
A splitting bijector splits an input `x` in two equal parts, `x1` and `x2` (see for instance Glow paper):
 that a `transferFro…
-
Hello,
I ran into a compilation issue that was triggered deep into Eigen ([here](https://gitlab.com/libeigen/eigen/-/blob/master/Eigen/src/Core/products/TriangularSolverMatrix.h#L124)) from e.g. th…
-
Good morning, Steven!
Thank you very much for your package and for having this website to solve the problems that arise with patternize.
I'm a fairly novice R user, and I'm trying to use your p…
-
Hi, great work!
I have some problems when I try to visualize the trajectory in picture like **Figure 4** in your paper. I got the original video (such as seq_eth.avi) and extract frames at 0.4s inter…
-
May I ask where the code corresponding to solving x_t-1 in line 5 of Algorithm 2 is located in the p_sample_ddim_conditional?
From the paper we know that the coefficient of the x_t term in line 5 o…
-
The main loop where depending on the parameters 80% of the time is spent is:
```
for ( unsigned iHioCycle = 0; iHioCycle < rnHioCycles; ++iHioCycle )
{
cudaKernelApplyHioDomainConstraints
…