结构化预测中LP松弛的训练和测试紧密性

Ofer Meshi, M. Mahdavi, Adrian Weller, D. Sontag
{"title":"结构化预测中LP松弛的训练和测试紧密性","authors":"Ofer Meshi, M. Mahdavi, Adrian Weller, D. Sontag","doi":"10.17863/CAM.242","DOIUrl":null,"url":null,"abstract":"Structured prediction is used in areas such as computer vision and natural language processing to predict structured outputs such as segmentations or parse trees. In these settings, prediction is performed by MAP inference or, equivalently, by solving an integer linear program. Because of the complex scoring functions required to obtain accurate predictions, both learning and inference typically require the use of approximate solvers. We propose a theoretical explanation to the striking observation that approximations based on linear programming (LP) relaxations are often tight on real-world instances. In particular, we show that learning with LP relaxed inference encourages integrality of training instances, and that tightness generalizes from train to test data.","PeriodicalId":14794,"journal":{"name":"J. Mach. Learn. Res.","volume":"1 1","pages":"13:1-13:34"},"PeriodicalIF":0.0000,"publicationDate":"2015-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"15","resultStr":"{\"title\":\"Train and Test Tightness of LP Relaxations in Structured Prediction\",\"authors\":\"Ofer Meshi, M. Mahdavi, Adrian Weller, D. Sontag\",\"doi\":\"10.17863/CAM.242\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Structured prediction is used in areas such as computer vision and natural language processing to predict structured outputs such as segmentations or parse trees. In these settings, prediction is performed by MAP inference or, equivalently, by solving an integer linear program. Because of the complex scoring functions required to obtain accurate predictions, both learning and inference typically require the use of approximate solvers. We propose a theoretical explanation to the striking observation that approximations based on linear programming (LP) relaxations are often tight on real-world instances. In particular, we show that learning with LP relaxed inference encourages integrality of training instances, and that tightness generalizes from train to test data.\",\"PeriodicalId\":14794,\"journal\":{\"name\":\"J. Mach. Learn. Res.\",\"volume\":\"1 1\",\"pages\":\"13:1-13:34\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-11-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"15\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"J. Mach. Learn. Res.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.17863/CAM.242\",\"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/10.17863/CAM.242","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 15

摘要

结构化预测用于计算机视觉和自然语言处理等领域,以预测结构化输出,如分割或解析树。在这些设置中,通过MAP推理执行预测,或者通过求解整数线性程序执行预测。由于获得准确预测所需的复杂评分函数,学习和推理通常都需要使用近似求解器。我们对基于线性规划(LP)松弛的近似在现实世界实例中通常是紧密的这一惊人的观察结果提出了一个理论解释。特别地,我们证明了LP松弛推理的学习促进了训练实例的完整性,并且紧密性从训练数据推广到测试数据。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Train and Test Tightness of LP Relaxations in Structured Prediction
Structured prediction is used in areas such as computer vision and natural language processing to predict structured outputs such as segmentations or parse trees. In these settings, prediction is performed by MAP inference or, equivalently, by solving an integer linear program. Because of the complex scoring functions required to obtain accurate predictions, both learning and inference typically require the use of approximate solvers. We propose a theoretical explanation to the striking observation that approximations based on linear programming (LP) relaxations are often tight on real-world instances. In particular, we show that learning with LP relaxed inference encourages integrality of training instances, and that tightness generalizes from train to test data.
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