nlesc-dirac/pytorch

Improved LBFGS and LBFGS-B optimizers in PyTorch.

47
/ 100
Emerging

This provides advanced optimization algorithms (LBFGS and LBFGS-B) for training deep learning models more efficiently. It takes your existing PyTorch neural network model and helps it learn faster or converge to a better solution than standard optimizers. This is for machine learning researchers, data scientists, and engineers who build and train deep learning models for tasks like image classification, scientific inverse problems, or clustering.

Use this if you are training deep neural networks in PyTorch and need more efficient convergence, especially for problems where traditional optimizers like Adam are too slow or get stuck.

Not ideal if you are working with extremely large batch sizes or require very simple, fast-to-implement optimizers that don't need fine-tuning.

deep-learning neural-network-training scientific-machine-learning federated-learning image-classification
No Package No Dependents
Maintenance 13 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

67

Forks

6

Language

Python

License

Apache-2.0

Last pushed

Mar 19, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nlesc-dirac/pytorch"

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