softmin/ReHLine-r

Regularized Composite ReLU-ReHU Loss Minimization with Linear Computation and Linear Convergence

21
/ 100
Experimental

This tool helps data scientists and analysts quickly find the best linear model for large datasets when dealing with complex, non-standard loss functions and specific constraints. You provide your data and the desired piecewise linear or quadratic loss function, and it outputs the optimal model coefficients. It's designed for practitioners who need to build robust predictive models efficiently.

No commits in the last 6 months.

Use this if you need to build linear predictive models on large datasets, incorporating custom loss functions or specific equality/inequality constraints, and require fast, guaranteed convergence.

Not ideal if your problem involves non-linear relationships that cannot be approximated by piecewise linear-quadratic functions, or if you prefer tree-based or deep learning models.

predictive-modeling statistical-modeling large-scale-data-analysis constrained-optimization quantitative-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

11

Forks

Language

C++

License

MIT

Last pushed

Feb 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/softmin/ReHLine-r"

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