patrick-kidger / patrick-kidger/diffrax
BacksolveAdjoint: include calculation of start and stop time gradients
Open
Nobody has claimed this yet.
feature
- Dominant language
- Python
- Stars
- 2.1k
- Forks
- 189
- Avg merge
- 3d 18h
- Merged PRs (30d)
- 1
Description
Is it possible to extend the current backsolveadjoint method such that gradients can be calculated for t1 (and t0) as well? I think this should be possible according the referenced paper https://arxiv.org/pdf/1806.07366.pdf.
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 current BacksolveAdjoint implementation and the referenced paper, https://arxiv.org/pdf/1806.07366.pdf, to understand how endpoint-time gradients should be incorporated. Done means the method can calculate gradients for t1 and t0 as requested, with behavior validated against the paper's formulation.
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
- 25/100