sun-umn/NCVX

NCVX: A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning

29
/ 100
Experimental

This package helps machine learning engineers and researchers solve complex optimization problems, especially those involving deep learning models with specific constraints. It takes your machine learning problem definition, including custom non-smooth constraints, and outputs optimized model parameters. This is ideal for those working on advanced machine learning models where standard optimizers fall short due to the complexity of the constraints.

No commits in the last 6 months.

Use this if you are a machine learning practitioner needing to train deep learning models under non-trivial, non-smooth constraints.

Not ideal if you are working with simple, unconstrained machine learning models or do not have experience with PyTorch.

deep-learning machine-learning-optimization constrained-optimization neural-network-training
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

37

Forks

2

Language

License

AGPL-3.0

Last pushed

Jul 27, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sun-umn/NCVX"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.