IRLS for Non-Smooth Robust Regression
Accompanying Github repository to NeurIPS 2022 paper.
MatrixIRLS
A data-efficient and scalable iteratively reweighted least squares method for low-rank matrix completion (see ICML 2020 Workshop paper and ICML 2021 paper), joint with Claudio Mayrink Verdun.
Contains framework to compare with many state-of-the-art matrix completion algorithms.
HM-IRLS
Code for paper Harmonic Mean Iteratively Reweighted Least Squares for Low-Rank Matrix Recovery, joint with Juliane Sigl.