-
See: https://arxiv.org/abs/2009.10113
-
GPML kernels: https://github.com/alshedivat/gpml/tree/master/cov
-
See: http://www3.ul.ie/gleesonj/Papers/SDEs/AM4062_notes6.pdf
We prefer a " Reflecting boundary condition".
(I added this because I don't want to lose track of the link.)
-
Add:
Geometric Brownian Motion:
- [x] cum_min
- [x] cum_max
- [x] cum_mean
Brownian Motion:
- [x] cum_min
- [x] cum_max
- [x] cum_mean
-
## DDPM
#### 1. propose the definition of forward equation. i.e.
and thus
#### 2. design a neutral network that has the below property to approximate the reverse(denoising) process
then we …
-
Depends on #3
Start with adding some unit tests. I'm sure given the size of the project this will be an ongoing issue for a while.
-
mainly parking a theoretical result
quote from Stephens' reference entry
"have shown that the asymptotic distributions of EDF statistics are the same as if both 𝜇 and 𝜎 were estimated"
This mea…
-
The Navier-Stokes equations, which describe the motion of fluid substances such as liquids and gases, are fundamental to the field of fluid dynamics. However, several challenging problems related to t…
-
To-do list so far:
Brownian motions:
- Switch to interval interface.
- [x] Brownian
- [x] BrownianInterval
- [x] BrownianPath (both Python and C++)
- [x] BrownianTree (both Pyt…
-
I am trying to follow the SDE example in Getting started section of diffrax's documentation, which is
```
import jax.random as jr
from diffrax import diffeqsolve, ControlTerm, Euler, MultiTerm, ODE…