patrick-kidger / patrick-kidger/diffrax

BacksolveAdjoint: include calculation of start and stop time gradients

Open
#244 3 comments 0 reactions 0 assignees View on GitHub

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

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.