https://github.com/rdyro/sensitivity_jax
JAX library for first- and second-order optimization sensitivity analysis
https://github.com/rdyro/sensitivity_jax
jax machine-learning optimization-tools
Last synced: 11 months ago
JSON representation
JAX library for first- and second-order optimization sensitivity analysis
- Host: GitHub
- URL: https://github.com/rdyro/sensitivity_jax
- Owner: rdyro
- License: mit
- Created: 2022-02-15T17:09:26.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2023-07-18T22:51:20.000Z (over 2 years ago)
- Last Synced: 2025-01-26T20:47:06.122Z (about 1 year ago)
- Topics: jax, machine-learning, optimization-tools
- Language: Python
- Homepage: https://rdyro.github.io/sensitivity_jax/
- Size: 2.43 MB
- Stars: 2
- Watchers: 2
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# sensitivity_jax
``sensitivity_jax`` is a package designed to allow taking first- and
**second-order** derivatives through optimization or any other fixed-point
process.
This package builds on top of [JAX](https://github.com/google/jax). We also
maintain an implementation in [PyTorch](https://pytorch.org/)
[here](https://rdyro.github.io/sensitivity_torch/).
## Documentation
[Documentation can be found here.](https://rdyro.github.io/sensitivity_jax/)
## Installation
Install using pip
```bash
$ pip install git+https://github.com/rdyro/sensitivity_jax.git
```
or from source
```bash
$ git clone git@github.com:rdyro/sensitivity_jax.git
$ cd sensitivity_jax
$ python3 setup.py install --user
```
### Testing
Run all unit tests using
```bash
$ python3 setup.py test
```