ReHLine

ReHLine is designed to be a computationally efficient and practically useful software package for large-scale empirical risk minimization (ERM) problems.

• Documentation: https://rehline-python.readthedocs.io
• Project homepage: https://rehline.github.io
• GitHub repo: https://github.com/softmin/ReHLine-python
• PyPi: https://pypi.org/project/rehline
• Paper: NeurIPS | 2023

The ReHLine solver has four appealing "linear properties":

• It applies to any convex piecewise linear-quadratic loss function, including the hinge loss, the check loss, the Huber loss, etc.
• In addition, it supports linear equality and inequality constraints on the parameter vector.
• The optimization algorithm has a provable linear convergence rate.
• The per-iteration computational complexity is linear in the sample size.

✨ New Features: Scikit-Learn Compatible Estimators

We are excited to introduce full scikit-learn compatibility! ReHLine now provides plq_Ridge_Classifier and plq_Ridge_Regressor estimators that integrate seamlessly with the entire scikit-learn ecosystem.

This means you can:

• Drop ReHLine estimators directly into your existing scikit-learn Pipeline.
• Perform robust hyperparameter tuning using GridSearchCV.
• Use standard scikit-learn evaluation metrics and cross-validation tools.

⌛ Benchmark (powered by benchopt)

Some existing problems of recent interest in statistics and machine learning can be solved by ReHLine, and we provide reproducible benchmark code and results at the ReHLine-benchmark repository.

Problem	Results
FairSVM	Result
ElasticQR	Result
RidgeHuber	Result
SVM	Result
Smoothed SVM	Result