VishnuVardhanKasireddy/curvature-optimizer
This project proposes CALR-NAG, a hybrid optimizer that enhances Adam-like adaptive updates with curvature-aware scaling and Nesterov acceleration. It approximates curvature using gradient magnitude, enabling second-order-like behavior without expensive Hessian computations. Experimental results on MNIST and CIFAR-10 demonstrate improved convergenc
Stars
—
Forks
—
Language
Jupyter Notebook
License
—
Last pushed
Apr 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/VishnuVardhanKasireddy/curvature-optimizer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
fastapi/fastapi
FastAPI framework, high performance, easy to learn, fast to code, ready for production
scikit-learn/scikit-learn
scikit-learn: machine learning in Python
probabl-ai/skore
Track your Data Science. Skore's open-source Python library accelerates ML model development...
Farama-Foundation/Gymnasium
An API standard for single-agent reinforcement learning environments, with popular reference...
WMD-group/SMACT
Python package to aid materials design and informatics