f-dangel/curvlinops

[DOC] Add influence functions example in the documentation

Open

#306 opened on May 26, 2026

View on GitHub
 (0 comments) (0 reactions) (0 assignees)Python (16 forks)github user discovery
documentationgood first issue

Repository metrics

Stars
 (70 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

It would be useful to show how to use curvlinops, specifically EKFAC, for influence functions. This would reduce friction for getting started with IFs using the library.

kronfluence has some good examples about influence functions (e.g. https://github.com/pomonam/kronfluence/blob/main/examples/uci/tutorial.ipynb) that we may take inspiration from.

Contributor guide

Research direction
Study the EKFAC implementation in curvlinops and the influence function tutorial from kronfluence, then create a Jupyter notebook tutorial demonstrating how to compute influence functions using EKFAC on a sample dataset, explaining each step and how it leverages the library's curvature matrices.
Tech stack
pythonpytorch
Domain
machine learningdocumentation
Issue type
Documentation
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonPyTorch
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70