《2016 Bundle-level type methods uniformly optimal for smooth and nonsmooth convex optimization》.pdf
- 1、本文档共45页,可阅读全部内容。
- 2、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。
- 3、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
查看更多
《2016 Bundle-level type methods uniformly optimal for smooth and nonsmooth convex optimization》.pdf
Math. Program., Ser. A
DOI 10.1007/s10107-013-0737-x
FULL LENGTH PAPER
Bundle-level type methods uniformly optimal
for smooth and nonsmooth convex optimization
Guanghui Lan
Received: 22 January 2013 / Accepted: 13 December 2013
© Springer-Verlag Berlin Heidelberg and Mathematical Optimization Society 2013
Abstract The main goal of this paper is to develop uniformly optimal first-order
methods for convex programming (CP). By uniform optimality we mean that the first-
order methods themselves do not require the input of any problem parameters, but can
still achieve the best possible iteration complexity bounds. By incorporating a multi-
step acceleration scheme into the well-known bundle-level method, we develop an
accelerated bundle-level method, and show that it can achieve the optimal complexity
for solving a general class of black-box CP problems without requiring the input of
any smoothness information, such as, whether the problem is smooth, nonsmooth or
weakly smooth, as well as the specific values of Lipschitz constant and smoothness
level. We then develop a more practical, restricted memory version of this method,
namely the accelerated prox-level (APL) method. We investigate the generalization
of the APL method for solving certain composite CP problems and an important class
of saddle-point problems recently studied by Nesterov (Math Program 103:127–152,
2005). We present promising numerical results for these new bundle-level methods
applied to solve certain classes of semidefinite programming and stochastic program-
ming problems.
Keywords Convex programming · Complexity · Bundle-level · Optimal methods
The paper is a combined version of the two manuscripts previously submitted to Mathematical
Programming, namely: “Bundle-type methods uniformly optimal for smooth and nonsmooth convex
optimization” and “Level methods uniformly optimal for composite and structured nonsmooth convex
optimization”.
The au
您可能关注的文档
- 《19 The Mean Sea Level Aquifer》.pdf
- 《1910.Java经典入门教程 》.pdf
- 《1983 Surrogate duality relaxation for job shop scheduling》.pdf
- 《1987 Scheduling jobs with release dates and tails on identical machines to minimize the makespan》.pdf
- 《1988 The Shifting Bottleneck Procedure for Job Shop Scheduling》.pdf
- 《1988level set》.pdf
- 《1990 B A real snow job》.pdf
- 《1990 Scheduling jobs with simple precedence constraints on parallel machines》.pdf
- 《1991 A branch and bound algorithm for job-shop scheduling》.pdf
- 《1992 An integrated model for job-shop planning and scheduling》.pdf
- 江苏省灌云高级中学2023-2024学年高三上学期第一次月考地理试题含答案.docx
- 备战2024年高考物理一轮重难点复习 第十三章 近代物理.docx
- 江苏省高邮市一中2021-2022学年高三上学期第一次月考语文试题(原卷版).docx
- 江苏省华罗庚中学2023-2024学年高三上学期12月阶段检测数学试卷含答案.docx
- 江苏省海门中学2023-2024学年高三上学期第一次调研考试地理试题及答案.docx
- 备战2024年高考物理一轮重难点复习 第九章 恒定电流.docx
- 江苏省高邮市2023-2024学年高三下学期3月学情调研数学试题含答案.docx
- 备战2024年高考物理一轮重难点复习 实验十一:探究影响感应电流方向的因素.docx
- 备战2024年高考物理一轮重难点复习 实验三:验证平行四边形定则.docx
- 备战2024年高考物理一轮重难点复习 第十四章 光.docx
文档评论(0)