https://github.com/alonfnt/bayex

Minimal Implementation of Bayesian Optimization in JAX
https://github.com/alonfnt/bayex

automatic-differentiation bayesian-optimization gaussian-process-regression jax python

Last synced: 3 months ago
JSON representation

Minimal Implementation of Bayesian Optimization in JAX

• Host: GitHub
• URL: https://github.com/alonfnt/bayex
• Owner: alonfnt
• License: mit
• Created: 2021-08-01T08:41:02.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2024-05-08T11:15:09.000Z (10 months ago)
• Last Synced: 2024-11-07T09:07:59.546Z (3 months ago)
• Topics: automatic-differentiation, bayesian-optimization, gaussian-process-regression, jax, python
• Language: Python
• Homepage:
• Size: 212 KB
• Stars: 83
• Watchers: 3
• Forks: 1
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Code of conduct: CODE_OF_CONDUCT.md
  • Citation: CITATION.cff

Awesome Lists containing this project

• awesome-jax - bayex - Bayesian Optimization powered by JAX. <img src="https://img.shields.io/github/stars/alonfnt/bayex?style=social" align="center"> (Libraries / New Libraries)
• awesome-jax - bayex - Minimal Implementation of Bayesian Optimization in JAX. <img src="https://img.shields.io/github/stars/alonfnt/bayex?style=social" align="center"> (Libraries)
• awesome-jax - bayex - Minimal Implementation of Bayesian Optimization in JAX. <img src="https://img.shields.io/github/stars/alonfnt/bayex?style=social" align="center"> (Libraries)

README

        
# Bayex: Minimal Bayesian Optimization in JAX

[![tests](https://github.com/alonfnt/bayex/actions/workflows/tests.yml/badge.svg)](https://github.com/alonfnt/bayex/actions/workflows/tests.yml)

>[!NOTE]

>Bayex is currently a minimal, personally developed implementation that requires further development for broader application. If you're interested in engaging with Jax and enhancing Bayex, your contributions would be highly welcomed and appreciated.



    

    



Bayex is a lightweight Bayesian optimization library designed for efficiency and flexibility, leveraging the power of JAX for high-performance numerical computations.

This library aims to provide an easy-to-use interface for optimizing expensive-to-evaluate functions through Gaussian Process (GP) models and various acquisition functions. Whether you're maximizing or minimizing your objective function, Bayex offers a simple yet powerful set of tools to guide your search for optimal parameters.

## Installation

Bayex can be installed using [PyPI](https://pypi.org/project/bayex/) via `pip`:

```

pip install bayex

```

## Usage

Using Bayex is quite simple despite its low level approach:

```python

import jax

import numpy as np

import bayex

def f(x):

    return -(1.4 - 3 * x) * np.sin(18 * x)

domain = {'x': bayex.domain.Real(0.0, 2.0)}

optimizer = bayex.Optimizer(domain=domain, maximize=True, acq='PI')

# Define some prior evaluations to initialise the GP.

params = {'x': [0.0, 0.5, 1.0]}

ys = [f(x) for x in params['x']

opt_state = optimizer.init(ys, params)

# Sample new points using Jax PRNG approach.

ori_key = jax.random.key(42)

for step in range(20):

    key = jax.random.fold_in(ori_key, step)

    new_params = optimizer.sample(key, opt_state)

    y_new = f(**new_params)

    opt_state = optimizer.fit(opt_state, y_new, new_params)

```

with the results being saved at `opt_state`.

## Contributing

We welcome contributions to Bayex! Whether it's adding new features, improving documentation, or reporting issues, please feel free to make a pull request or open an issue.

## License

Bayex is licensed under the MIT License. See the ![LICENSE](LICENSE) file for more details.