google / google/jaxopt

LevenbergMarquardt do not seems to work with non-flat input.

Open
#505 2 comments 0 reactions 1 assignee Claimed by @amir-saadat View on GitHub
Dominant language
Python
Stars
1.1k
Forks
76
Avg merge
2d 21h
Merged PRs (30d)
1

Description

GaussNewton is working as intended with Pytree. I would expect the same for LM. Instead, I had to flatten the array to make it properly works.

![image](https://github.com/google/jaxopt/assets/26026137/31e9e0de-f7e6-405d-b0c7-18ce08fb317c)

The errors appear at line 445. The error comes from the fact that the pytree of params and vec do not match.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.