High-Dimensional Fused Lasso Regression Using Majorization–Minimization and Parallel Processing

Donghyeon Yu, Joong‐Ho Won, Taehoon Lee, Johan Lim, Sungroh YoonFigshare 2015 · DOI · OpenAlex

Abstract

In this article, we propose a majorization–minimization (MM) algorithm for high-dimensional fused lasso regression (FLR) suitable for parallelization using graphics processing units (GPUs). The MM algorithm is stable and flexible as it can solve the FLR problems with various types of design matrices and penalty structures within a few tens of iterations. We also show that the convergence of the proposed algorithm is guaranteed. We conduct numerical studies to compare our algorithm with other existing algorithms, demonstrating that the proposed MM algorithm is competitive in many settings including the two-dimensional FLR with arbitrary design matrices. The merit of GPU parallelization is also exhibited. Supplementary materials are available online.
BibTeX
@inproceedings{yu2015high,
  author = {Donghyeon Yu and Joong‐Ho Won and Taehoon Lee and Johan Lim and Sungroh Yoon},
  title = {{High-Dimensional Fused Lasso Regression Using Majorization–Minimization and Parallel Processing}},
  booktitle = {Figshare},
  year = {2015},
  doi = {10.6084/m9.figshare.1378871},
}

Loading related content...

Figure