https://github.com/mfschubert/mewtax

https://github.com/mfschubert/mewtax

Last synced: 15 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/mfschubert/mewtax
• Owner: mfschubert
• License: mit
• Created: 2024-01-11T17:08:29.000Z (10 months ago)
• Default Branch: main
• Last Pushed: 2024-06-14T19:53:05.000Z (5 months ago)
• Last Synced: 2024-06-15T19:52:34.460Z (5 months ago)
• Language: Python
• Size: 27.3 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Differentiable minimization in jax using Newton's method

`v0.0.1`

This project essentially repackages code from the [implicit layers tutorial](https://implicit-layers-tutorial.org/implicit_functions/) to provide a `minimize_newton` function.

Given a function `fn(params, z)`, it finds the `z_star` which minimizes `fn` for given `params`. Further, the gradient of the solution with respect to `params` can be computed; this is done using a custom vjp rule, as shown in the tutorial.

## Installation

mewtax can be installed via pip:

```

pip install mewtax

```