JAX implementation of Competitive Gradient Descent algorithms
Project description
JAX-CGD
JAX implementation of Competitive Gradient Descent algorithms for minimax optimization problems.
Features
- ACGD (Adaptive Competitive Gradient Descent): An adaptive variant of competitive gradient descent with momentum
- BCGD (Basic Competitive Gradient Descent): Standard competitive gradient descent algorithm
- Flexible Solvers: Support for different linear algebra solvers (CG, GMRES)
- JAX Integration: Built on JAX for automatic differentiation and JIT compilation
Installation
pip install jax-cgd
Algorithms
ACGD (Adaptive Competitive Gradient Descent)
- Includes momentum and adaptive learning rates
- Better convergence properties for complex minimax problems
- Configurable exponential decay rate (beta) and numerical stability (eps)
BCGD (Basic Competitive Gradient Descent)
- Standard competitive gradient descent
- Simpler implementation for basic minimax optimization
Requirements
- Python >= 3.10
- JAX >= 0.5.1
- NumPy
- Flax >= 1.10.0
License
MIT License
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
jax_cgd-1.0.4.tar.gz
(8.2 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file jax_cgd-1.0.4.tar.gz.
File metadata
- Download URL: jax_cgd-1.0.4.tar.gz
- Upload date:
- Size: 8.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.10.16
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
5e9709bcdcecd4006a620ae751c93c8199c55be7e9e3f38e28d567cbe11b9e53
|
|
| MD5 |
d0de8623021ccce1302c2d95538ee790
|
|
| BLAKE2b-256 |
0cb8ce3d74165023d9cf02288c0cb70939f2b13997679c4bc0064a46af15a9ce
|
File details
Details for the file jax_cgd-1.0.4-py3-none-any.whl.
File metadata
- Download URL: jax_cgd-1.0.4-py3-none-any.whl
- Upload date:
- Size: 9.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.10.16
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f3b7775a5c87cb0765ee5d5a202f0a03a488291f89924d0ebc7b96ee830574c3
|
|
| MD5 |
1778e3e43a27af6c1b1487617069006a
|
|
| BLAKE2b-256 |
733be114ebaeb38c0d4311ef6979fafbc121f852a79e1fa74bf496208911059d
|
