-
I wonder if it would make the subsequent simulation easier if we start with quasi-random positions rather than uniformly random ones. Something like a Halton sequence: https://en.wikipedia.org/wiki/Ha…
-
Both sequences don't have (0, ...) as their first point. This is particularly wrong for Sobol' as it requires the number of samples to be a power of 2. Not having the zero will break the balance prope…
tupui updated
3 years ago
-
Both sequences don't have (0, ...) as their first point. This is particularly wrong for Sobol' as it requires the number of samples to be a power of 2. Not having the zero will break the balance prope…
tupui updated
4 years ago
-
* via textures
or
* via halton sequences (@edwinRNDR)
### Resources
* [The importance of good noise](http://blog.tuxedolabs.com/2018/12/07/the-importance-of-good-noise.html)
* [3D blue noise](h…
-
The current isotropic initial condition uses `scipy.spatial.transform.Rotation.random` which seems to be constructed by sampling normal distributions in quaternion space (scipy `Rotation`s are impleme…
-
Hoffman et al introduced ChEES-HMC in http://proceedings.mlr.press/v130/hoffman21a/hoffman21a.pdf. It's one answer to the problem of the wastefulness of NUTS when sampling many chains discussed in htt…
-
We should include the implementations of the Almost convex sets and the double zig-zag chain at some point.
-
#### Is your feature request related to a problem? Please describe
I'd like to run this R code in python statsmodels:
```R
model
-
Now that there is a `scipy.stats.qmc` module thanks to #10844, it might be worth looking into moving some of the critical parts to either Cython or Pythran.
Candidates:
* `scipy.stats.qmc.Sobol` i…
tupui updated
2 years ago
-
### What happened?
Here are the first 4 points of the Faure sequence in the current's master:
| | y0 | y1 |
|---|---|---|
|0 | 0.5 | 0.5|
|1 | 0.25 | 0.75|
|2 | 0.75 | 0.25|
|3 | 0.125 | 0.…