巴拿赫空间中正规化学习问题的对偶方法

Raymond Cheng, Rui Wang, Yuesheng Xu
{"title":"巴拿赫空间中正规化学习问题的对偶方法","authors":"Raymond Cheng, Rui Wang, Yuesheng Xu","doi":"arxiv-2312.05734","DOIUrl":null,"url":null,"abstract":"Learning methods in Banach spaces are often formulated as regularization\nproblems which minimize the sum of a data fidelity term in a Banach norm and a\nregularization term in another Banach norm. Due to the infinite dimensional\nnature of the space, solving such regularization problems is challenging. We\nconstruct a direct sum space based on the Banach spaces for the data fidelity\nterm and the regularization term, and then recast the objective function as the\nnorm of a suitable quotient space of the direct sum space. In this way, we\nexpress the original regularized problem as an unregularized problem on the\ndirect sum space, which is in turn reformulated as a dual optimization problem\nin the dual space of the direct sum space. The dual problem is to find the\nmaximum of a linear function on a convex polytope, which may be solved by\nlinear programming. A solution of the original problem is then obtained by\nusing related extremal properties of norming functionals from a solution of the\ndual problem. Numerical experiments are included to demonstrate that the\nproposed duality approach leads to an implementable numerical method for\nsolving the regularization learning problems.","PeriodicalId":501061,"journal":{"name":"arXiv - CS - Numerical Analysis","volume":"1 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Duality Approach to Regularized Learning Problems in Banach Spaces\",\"authors\":\"Raymond Cheng, Rui Wang, Yuesheng Xu\",\"doi\":\"arxiv-2312.05734\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Learning methods in Banach spaces are often formulated as regularization\\nproblems which minimize the sum of a data fidelity term in a Banach norm and a\\nregularization term in another Banach norm. Due to the infinite dimensional\\nnature of the space, solving such regularization problems is challenging. We\\nconstruct a direct sum space based on the Banach spaces for the data fidelity\\nterm and the regularization term, and then recast the objective function as the\\nnorm of a suitable quotient space of the direct sum space. In this way, we\\nexpress the original regularized problem as an unregularized problem on the\\ndirect sum space, which is in turn reformulated as a dual optimization problem\\nin the dual space of the direct sum space. The dual problem is to find the\\nmaximum of a linear function on a convex polytope, which may be solved by\\nlinear programming. A solution of the original problem is then obtained by\\nusing related extremal properties of norming functionals from a solution of the\\ndual problem. Numerical experiments are included to demonstrate that the\\nproposed duality approach leads to an implementable numerical method for\\nsolving the regularization learning problems.\",\"PeriodicalId\":501061,\"journal\":{\"name\":\"arXiv - CS - Numerical Analysis\",\"volume\":\"1 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-12-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Numerical Analysis\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2312.05734\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Numerical Analysis","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2312.05734","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

巴拿赫空间中的学习方法通常被表述为正则化问题,即最小化巴拿赫规范中的数据保真度项与另一巴拿赫规范中的正则化项之和。由于空间的无限维特性,解决此类正则化问题具有挑战性。我们根据数据保真度项和正则化项的巴拿赫空间构建了一个直接求和空间,然后将目标函数重新转换为直接求和空间的合适商空间的规范。这样,我们就把原来的正则化问题表达为直接求和空间上的非正则化问题,而直接求和空间上的非正则化问题又被重新表述为直接求和空间对偶空间上的对偶优化问题。对偶问题是在凸多面体上寻找线性函数的最大值,可以通过线性规划来解决。然后,利用对偶问题解中的规范化函数的相关极值性质,得到原始问题的解。实验证明,所提出的对偶方法是解决正则化学习问题的一种可实施的数值方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Duality Approach to Regularized Learning Problems in Banach Spaces
Learning methods in Banach spaces are often formulated as regularization problems which minimize the sum of a data fidelity term in a Banach norm and a regularization term in another Banach norm. Due to the infinite dimensional nature of the space, solving such regularization problems is challenging. We construct a direct sum space based on the Banach spaces for the data fidelity term and the regularization term, and then recast the objective function as the norm of a suitable quotient space of the direct sum space. In this way, we express the original regularized problem as an unregularized problem on the direct sum space, which is in turn reformulated as a dual optimization problem in the dual space of the direct sum space. The dual problem is to find the maximum of a linear function on a convex polytope, which may be solved by linear programming. A solution of the original problem is then obtained by using related extremal properties of norming functionals from a solution of the dual problem. Numerical experiments are included to demonstrate that the proposed duality approach leads to an implementable numerical method for solving the regularization learning problems.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信