多类稀疏线性分类器的泛化误差范围

Tomer Levy, F. Abramovich
{"title":"多类稀疏线性分类器的泛化误差范围","authors":"Tomer Levy, F. Abramovich","doi":"10.48550/arXiv.2204.06264","DOIUrl":null,"url":null,"abstract":"We consider high-dimensional multiclass classification by sparse multinomial logistic regression. Unlike binary classification, in the multiclass setup one can think about an entire spectrum of possible notions of sparsity associated with different structural assumptions on the regression coefficients matrix. We propose a computationally feasible feature selection procedure based on penalized maximum likelihood with convex penalties capturing a specific type of sparsity at hand. In particular, we consider global sparsity, double row-wise sparsity, and low-rank sparsity, and show that with the properly chosen tuning parameters the derived plug-in classifiers attain the minimax generalization error bounds (in terms of misclassification excess risk) within the corresponding classes of multiclass sparse linear classifiers. The developed approach is general and can be adapted to other types of sparsity as well.","PeriodicalId":14794,"journal":{"name":"J. Mach. Learn. Res.","volume":"10 1","pages":"151:1-151:35"},"PeriodicalIF":0.0000,"publicationDate":"2022-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Generalization Error Bounds for Multiclass Sparse Linear Classifiers\",\"authors\":\"Tomer Levy, F. Abramovich\",\"doi\":\"10.48550/arXiv.2204.06264\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We consider high-dimensional multiclass classification by sparse multinomial logistic regression. Unlike binary classification, in the multiclass setup one can think about an entire spectrum of possible notions of sparsity associated with different structural assumptions on the regression coefficients matrix. We propose a computationally feasible feature selection procedure based on penalized maximum likelihood with convex penalties capturing a specific type of sparsity at hand. In particular, we consider global sparsity, double row-wise sparsity, and low-rank sparsity, and show that with the properly chosen tuning parameters the derived plug-in classifiers attain the minimax generalization error bounds (in terms of misclassification excess risk) within the corresponding classes of multiclass sparse linear classifiers. The developed approach is general and can be adapted to other types of sparsity as well.\",\"PeriodicalId\":14794,\"journal\":{\"name\":\"J. Mach. Learn. Res.\",\"volume\":\"10 1\",\"pages\":\"151:1-151:35\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-04-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"J. Mach. Learn. Res.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2204.06264\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"J. Mach. Learn. Res.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2204.06264","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

利用稀疏多项式逻辑回归研究高维多类分类问题。与二元分类不同,在多类设置中,可以考虑与回归系数矩阵上不同结构假设相关的稀疏性概念的整个范围。我们提出了一种计算上可行的基于凸惩罚的最大似然的特征选择方法,该方法可以捕获手边特定类型的稀疏性。特别地,我们考虑了全局稀疏性、双行稀疏性和低秩稀疏性,并表明在适当选择调优参数的情况下,派生的插件分类器在相应的多类稀疏线性分类器中获得了最小最大泛化误差界限(就误分类超额风险而言)。所开发的方法是通用的,也可以适用于其他类型的稀疏性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Generalization Error Bounds for Multiclass Sparse Linear Classifiers
We consider high-dimensional multiclass classification by sparse multinomial logistic regression. Unlike binary classification, in the multiclass setup one can think about an entire spectrum of possible notions of sparsity associated with different structural assumptions on the regression coefficients matrix. We propose a computationally feasible feature selection procedure based on penalized maximum likelihood with convex penalties capturing a specific type of sparsity at hand. In particular, we consider global sparsity, double row-wise sparsity, and low-rank sparsity, and show that with the properly chosen tuning parameters the derived plug-in classifiers attain the minimax generalization error bounds (in terms of misclassification excess risk) within the corresponding classes of multiclass sparse linear classifiers. The developed approach is general and can be adapted to other types of sparsity as well.
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