Metadata-Version: 2.5
Name: pydegas
Version: 0.0.1
Summary: Fit the parameters of probabilistic programs with gradient descent, without sampling.
Project-URL: Source, https://github.com/degas-tool/pydegas
Project-URL: Issues, https://github.com/degas-tool/pydegas/issues
Project-URL: Paper, https://arxiv.org/abs/2601.15167
Author: Oguzhan Merttürk, Francesca Randone
License-Expression: MIT
License-File: LICENSE
Keywords: DeGAS,SOGA,differentiable programming,gaussian mixture,optimization,probabilistic programming,pytorch
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Mathematics
Classifier: Typing :: Typed
Requires-Python: >=3.12
Requires-Dist: antlr4-python3-runtime==4.10
Requires-Dist: botorch>=0.9.1
Requires-Dist: numpy>=1.26
Requires-Dist: scikit-learn>=1.3.1
Requires-Dist: torch>=2.2
