Accelerated dual-averaging primal–dual method for composite convex minimization

Conghui Tan, Yuqiu Qian, Shiqian Ma, Tong Zhang

Research output: Contribution to journalArticlepeer-review


Dual averaging-type methods are widely used in industrial machine learning applications due to their ability to promoting solution structure (e.g. sparsity) efficiently. In this paper, we propose a novel accelerated dual-averaging primal–dual algorithm for minimizing a composite convex function. We also derive a stochastic version of the proposed method that solves empirical risk minimization, and its advantages on handling sparse data are demonstrated both theoretically and empirically.

Original languageEnglish (US)
Pages (from-to)741-766
Number of pages26
JournalOptimization Methods and Software
Issue number4
StatePublished - Jul 3 2020
Externally publishedYes


  • acceleration
  • Dual averaging algorithm
  • empirical risk minimization
  • primal–dual
  • sparse data

ASJC Scopus subject areas

  • Software
  • Control and Optimization
  • Applied Mathematics


Dive into the research topics of 'Accelerated dual-averaging primal–dual method for composite convex minimization'. Together they form a unique fingerprint.

Cite this