benchopt / benchopt/benchmark_lasso
[ENH] - more solvers to be added (Grafting + Subgradient)
- Dominant language
- Python
- Stars
- 14
- Forks
- 24
- PR merge metrics
- No merged PRs in 30d
Description
In the paper "Least Squares Optimization with L1-Norm Regularization" [https://www.cs.ubc.ca/~schmidtm/Documents/2005_Notes_Lasso.pdf](https://www.cs.ubc.ca/~schmidtm/Documents/2005_Notes_Lasso.pdf)
Mark himdtm provided a large list of (possibly old) lasso solvers, with implementation in matlab: [https://www.cs.ubc.ca/~schmidtm/Software/lasso.html](https://www.cs.ubc.ca/~schmidtm/Documents/2005_Notes_Lasso.pdf)
Some of them could be ported to Python (or even Julia), at least for the penalized version :
- [ ] Grafting : https://www.jmlr.org/papers/volume3/perkins03a/perkins03a.pdf
- [ ] SubGradient
in particular.
This mostlikely would be for historical comparison, not expecting the solver to be state-of-the-art.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.