ADMM for least square problems with pairwise-difference penalties for coefficient grouping

Soohee Park, Seung Jun Shin

Research output: Contribution to journalArticlepeer-review

Abstract

In the era of bigdata, scalability is a crucial issue in learning models. Among many others, the Alternating Direction of Multipliers (ADMM, Boyd et al., 2011) algorithm has gained great popularity in solving large-scale problems efficiently. In this article, we propose applying the ADMM algorithm to solve the least square problem penalized by the pairwise-difference penalty, frequently used to identify group structures among coefficients. ADMM algorithm enables us to solve the high-dimensional problem efficiently in a unified fashion and thus allows us to employ several different types of penalty functions such as LASSO, Elastic Net, SCAD, and MCP for the penalized problem. Additionally, the ADMM algorithm naturally extends the algorithm to distributed computation and real-time updates, both desirable when dealing with large amounts of data.

Original languageEnglish
Pages (from-to)441-451
Number of pages11
JournalCommunications for Statistical Applications and Methods
Volume29
Issue number4
DOIs
Publication statusPublished - 2022

Keywords

  • Alternating direction of multipliers
  • Grouping coefficients
  • High-dimensional data
  • Real-time update

ASJC Scopus subject areas

  • Statistics and Probability
  • Modelling and Simulation
  • Finance
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'ADMM for least square problems with pairwise-difference penalties for coefficient grouping'. Together they form a unique fingerprint.

Cite this