AidinHamedi/Optimizer-Benchmark

A benchmarking suite for evaluating PyTorch optimization algorithms on 2D mathematical functions (optimizer benchmark)

30
/ 100
Emerging

This tool helps machine learning engineers and researchers evaluate how different optimization algorithms perform. You provide various PyTorch optimizers, and it generates visual trajectories and performance rankings based on how well they navigate a set of 2D mathematical functions. This helps practitioners understand the characteristics of optimizers outside of real-world neural network training scenarios.

Use this if you are a machine learning researcher or engineer interested in the theoretical performance and behavior of PyTorch optimization algorithms on synthetic landscapes.

Not ideal if you need to choose an optimizer for a specific real-world neural network training task, as these results may not directly translate to practical applications.

optimization-benchmarking machine-learning-research algorithm-evaluation mathematical-optimization pytorch-ecosystem
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Python

License

MIT

Last pushed

Feb 03, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AidinHamedi/Optimizer-Benchmark"

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