patrick-kidger / patrick-kidger/diffrax

Support integral losses with `BacksolveAdjoint`

Open
#69 0 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

c.f. the discussion in #60.

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 with the discussion in issue #60, then trace the BacksolveAdjoint entry point in the Diffrax source. Determine the intended behavior for integral losses and identify the relevant validation or test coverage; the work is done when that behavior is supported and verified.

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
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.