CONVERGENCE RATE OF GRADIENT DESCENT METHOD FOR MULTI-OBJECTIVE OPTIMIZATION
文献类型:期刊论文
作者 | Zeng, Liaoyuan2; Dai, Yuhong2; Huang, Yakui1 |
刊名 | JOURNAL OF COMPUTATIONAL MATHEMATICS
![]() |
出版日期 | 2019 |
卷号 | 37期号:5页码:689-703 |
关键词 | Multi-objective optimization Gradient descent Convergence rate |
ISSN号 | 0254-9409 |
DOI | 10.4208/jcm.1808-m2017-0214 |
英文摘要 | The convergence rate of the gradient descent method is considered for unconstrained multi-objective optimization problems (MOP). Under standard assumptions, we prove that the gradient descent method with constant stepsizes converges sublinearly when the objective functions are convex and the convergence rate can be strengthened to be linear if the objective functions are strongly convex. The results are also extended to the gradient descent method with the Armijo line search. Hence, we see that the gradient descent method for MOP enjoys the same convergence properties as those for scalar optimization. |
资助项目 | Chinese Natural Science Foundation[11631013] ; Chinese Natural Science Foundation[11971372] ; National 973 Program of China[2015CB856002] |
WOS研究方向 | Mathematics |
语种 | 英语 |
WOS记录号 | WOS:000504737600006 |
出版者 | GLOBAL SCIENCE PRESS |
源URL | [http://ir.amss.ac.cn/handle/2S8OKBNM/50442] ![]() |
专题 | 中国科学院数学与系统科学研究院 |
通讯作者 | Dai, Yuhong |
作者单位 | 1.Hebei Univ Technol, Sch Sci, Tianjin 300401, Peoples R China 2.Chinese Acad Sci, State Key Lab Sci & Engn Comp, Inst Computat Math & Sci Engn Comp, Acad Math & Syst Sci, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Zeng, Liaoyuan,Dai, Yuhong,Huang, Yakui. CONVERGENCE RATE OF GRADIENT DESCENT METHOD FOR MULTI-OBJECTIVE OPTIMIZATION[J]. JOURNAL OF COMPUTATIONAL MATHEMATICS,2019,37(5):689-703. |
APA | Zeng, Liaoyuan,Dai, Yuhong,&Huang, Yakui.(2019).CONVERGENCE RATE OF GRADIENT DESCENT METHOD FOR MULTI-OBJECTIVE OPTIMIZATION.JOURNAL OF COMPUTATIONAL MATHEMATICS,37(5),689-703. |
MLA | Zeng, Liaoyuan,et al."CONVERGENCE RATE OF GRADIENT DESCENT METHOD FOR MULTI-OBJECTIVE OPTIMIZATION".JOURNAL OF COMPUTATIONAL MATHEMATICS 37.5(2019):689-703. |
入库方式: OAI收割
来源:数学与系统科学研究院
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。