Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1080/10556788.2020.1713779 | OPTIMIZATION METHODS & SOFTWARE |
Keywords | DocType | Volume |
Dual averaging algorithm,primal-dual,empirical risk minimization,acceleration,sparse data,90c25 | Journal | 35 |
Issue | ISSN | Citations |
SP4 | 1055-6788 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tan Conghui | 1 | 0 | 0.34 |
Qian, Yuqiu | 2 | 18 | 2.68 |
Shiqian Ma | 3 | 1068 | 63.48 |
Zhang, Tong | 4 | 7126 | 611.43 |