Benchopt
BenchOpt is a benchmarking suite for optimization algorithms. It is built for simplicity, transparency, and reproducibility.
Benchopt is a collaborative framework for creating reproducible benchmarks of optimization algorithms in machine learning. It automates the tedious work of implementing, running, and comparing different solvers across programming languages and hardware, ensuring that benchmarks are transparent and can be easily extended by the community.
The framework handles the complexity of fair comparison—managing dependencies, standardizing interfaces, and collecting performance metrics—so researchers can focus on understanding which methods work best for their problems. Benchmarks cover standard ML tasks like logistic regression, LASSO, and neural network training, providing practical insights beyond theoretical comparisons.
Citation
@inproceedings{moreau2022,
author = {Moreau, Thomas and Massias, Mathurin and Gramfort, Alexandre
and Ablin, Pierre and Bannier, Pierre-Antoine and Charlier, Benjamin
and Dagréou, Mathieu and Dupré la Tour, Tom and Durif, Ghislain and
F. Dantas, Cassio and Klopfenstein, Quentin and Larsson, Johan and
Lai, En and Lefort, Tanguy and Malézieux, Benoit and Moufad, Badr
and T. Nguyen, Binh and Rakotomamonjy, Alain and Ramzi, Zaccharie
and Salmon, Joseph and Vaiter, Samuel},
editor = {Koyejo, S. and Mohamed, S. and Agarwal, A. and Belgrave, D.
and Cho, K. and Oh, A.},
title = {Benchopt: Reproducible, Efficient and Collaborative
Optimization Benchmarks},
booktitle = {Advances in Neural Information Processing Systems},
volume = {35},
pages = {25404-25421},
date = {2022-12-06},
url = {https://papers.nips.cc/paper_files/paper/2022/hash/a30769d9b62c9b94b72e21e0ca73f338-Abstract-Conference.html},
doi = {10.52202/068431-1842},
langid = {en}
}