patrick-kidger / patrick-kidger/diffrax
Second-Order Neural ODEs
Open
Nobody has claimed this yet.
question
- Dominant language
- Python
- Stars
- 2.1k
- Forks
- 189
- Avg merge
- 3d 18h
- Merged PRs (30d)
- 1
Description
I recently came across this paper from last years NeurIPS
https://ghliu.github.io/assets/pdf/neurips-snopt-slides.pdf
https://github.com/ghliu/snopt
I was wondering if there are any plans to extend Diffrax to support this improvement to the standard Neural ODE approach.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the linked NeurIPS slides and the ghliu/snopt repository to understand the proposed second-order Neural ODE approach. Then assess how it could fit into Diffrax; the issue names no Diffrax files or tests and provides no concrete acceptance criterion, so the intended implementation scope would need clarification.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100