patrick-kidger / patrick-kidger/diffrax
Adjoint hessian method
Open
Nobody has claimed this yet.
question
- Dominant language
- Python
- Stars
- 2.1k
- Forks
- 189
- Avg merge
- 3d 18h
- Merged PRs (30d)
- 1
Description
Hello,
Thanks a lot for sharing this lib.
I wonder if you used adjoint method to calculate hessian as calculating gradient ? This adjoint hessian method could be more efficient than jax.hessian ?
Thanks for your reply in advance.
Best,
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
The issue asks whether Diffrax supports an adjoint Hessian method and whether it could be more efficient than jax.hessian. No files, tests, or entry points are identified, so first determine the relevant differentiation API and documentation location. Done would require a maintainer-approved scope, implementation approach, and comparison against jax.hessian.
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