摘要
FastLORS is a software package that implements a new algorithm to solve sparse multivariate regression for expression quantitative trait loci (eQTLs) mapping. FastLORS solves the same optimization problem as LORS, an existing popular algorithm. The optimization problem is solved through inexact block coordinate descent with updates by proximal gradient steps, which reduces the computational cost compared with LORS. We apply LORS and FastLORS to a real dataset for eQTL mapping and demonstrate that FastLORS delivers comparable results with LORS in much less computing time.
原文 | English |
---|---|
文章編號 | e265 |
期刊 | Stat |
卷 | 9 |
發行號 | 1 |
DOIs | |
出版狀態 | Published - 2020 |
All Science Journal Classification (ASJC) codes
- 統計與概率
- 統計、概率和不確定性