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-1.0.3.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-1.0.3.tar.gz.
File metadata
- Download URL: jax_cgd-1.0.3.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 |
c10b6bb633a5345df1ed3f761efd62db8e003002ee02b84ecd1c2da64c0b8373
|
|
| MD5 |
67505341e156e98d054ee49e45b4aa6c
|
|
| BLAKE2b-256 |
2d35868a676dcfed31ceab621f8343f84b2619ddcad321ef9e39e36d5d8df052
|
File details
Details for the file jax_cgd-1.0.3-py3-none-any.whl.
File metadata
- Download URL: jax_cgd-1.0.3-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 |
de342c1f283896e03045611e8c664a93131d4a6662ce44f229ab5682857cbfea
|
|
| MD5 |
df3dc900d35ffa70cd0e09e370fcde88
|
|
| BLAKE2b-256 |
3d442a0432112c6342bf7b4fd7f627db1cffb6dffa2cacfbd2ae5e774b32da89
|
