equinox and optimistix

Optimistix is a specialized optimization library that builds on top of Equinox, providing nonlinear solving capabilities for users of the Equinox neural network framework—making them complements that are typically used together.

equinox
71
Verified
optimistix
65
Established
Maintenance 13/25
Adoption 15/25
Maturity 25/25
Community 18/25
Maintenance 13/25
Adoption 12/25
Maturity 25/25
Community 15/25
Stars: 2,814
Forks: 180
Downloads:
Commits (30d): 5
Language: Python
License: Apache-2.0
Stars: 553
Forks: 45
Downloads:
Commits (30d): 3
Language: Python
License: Apache-2.0
No risk flags
No risk flags

About equinox

patrick-kidger/equinox

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

Equinox helps machine learning engineers and scientists build and train neural networks and scientific models using JAX. It takes your model definitions and data, then outputs trained models ready for deployment. This is for users already comfortable with JAX who need a flexible tool for advanced model building.

deep-learning-research scientific-modeling neural-network-design jax-development model-training

About optimistix

patrick-kidger/optimistix

Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/

Optimistix helps developers using JAX with advanced numerical computations by providing tools for solving complex mathematical problems like root-finding, minimization, and least squares. It takes mathematical functions and equations as input and produces precise solutions for these problems, enabling efficient development of scientific computing and machine learning applications. This tool is for JAX developers, machine learning engineers, and researchers who need robust and flexible optimization capabilities.

JAX-development numerical-optimization scientific-computing machine-learning-engineering mathematical-modeling

Scores updated daily from GitHub, PyPI, and npm data. How scores work