-
Notifications
You must be signed in to change notification settings - Fork 236
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
A tutorial for integrating ODEs multiple times #1450
Comments
The contribution would be awesome! Currently, we only have an example for Lotka-Volterra. A tutorial with motivations for your usage case would be super helpful for users. |
@A2P2 hi! I think this is a good contribution and I am also somewhat have similar issues now. |
@zz100chan I do have a draft written, see it attached. I tried to follow the style of the current Lotka-Volterra tutorial. Let me know if it works for you and if something is not clear. Once again, it's in a draft state at the moment. Attached as a zip file. I've tried to implement a few things: 1) integrate with different initial conditions, 2) allowed to have missing values in the data. I use regularly spaced time arrays, but it's not a must. The MCMC is somewhat slow. I've turned on @fehiepsi I'm glad to finish the tutorial properly if you provide some feedback. Once again, my apologies for disappearing. |
Could you make a version of it on https://gist.github.com/? |
Thank you! I'll take a look later of the week. |
Hi @A2P2, the example looks great. In the tutorial, it would be nice to include some introduction to the model, how the dataset looks like, and motivation for integrating ODEs multiple times. |
@fehiepsi thanks for checking it quickly. I've added a short motivation to the gist, I'll add the dataset description later. |
Could you turn it into a (probably short?) tutorial, rather than an example? We have several tutorials here (those without |
Will do! |
@fehiepsi here is the tutorial version on colab, let me know what you think. |
super cool, @A2P2 ! |
Hi,
I'm wondering if there is a need to contribute with a tutorial for integrating ODEs multiple times based on different initial conditions. It's also possible to extend the current Lotka-Volterra example instead.
I oriented myself about the usage of jax.vmap for this purpose with the help of forums:
https://forum.pyro.ai/t/parallelization-plate-and-odes/2763
https://forum.pyro.ai/t/making-a-for-loop-more-efficient/3437/22
Is it of interest? Let me know what you think.
The text was updated successfully, but these errors were encountered: