用于大规模动态学习的Langevinized集成卡尔曼滤波器

IF 1.5 3区 数学 Q2 STATISTICS & PROBABILITY
Peiyi Zhang, Qifan Song, F. Liang
{"title":"用于大规模动态学习的Langevinized集成卡尔曼滤波器","authors":"Peiyi Zhang, Qifan Song, F. Liang","doi":"10.5705/ss.202022.0172","DOIUrl":null,"url":null,"abstract":"","PeriodicalId":49478,"journal":{"name":"Statistica Sinica","volume":"1 1","pages":""},"PeriodicalIF":1.5000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"A Langevinized Ensemble Kalman Filter for Large-Scale Dynamic Learning\",\"authors\":\"Peiyi Zhang, Qifan Song, F. Liang\",\"doi\":\"10.5705/ss.202022.0172\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\",\"PeriodicalId\":49478,\"journal\":{\"name\":\"Statistica Sinica\",\"volume\":\"1 1\",\"pages\":\"\"},\"PeriodicalIF\":1.5000,\"publicationDate\":\"2023-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Statistica Sinica\",\"FirstCategoryId\":\"100\",\"ListUrlMain\":\"https://doi.org/10.5705/ss.202022.0172\",\"RegionNum\":3,\"RegionCategory\":\"数学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"STATISTICS & PROBABILITY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Statistica Sinica","FirstCategoryId":"100","ListUrlMain":"https://doi.org/10.5705/ss.202022.0172","RegionNum":3,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"STATISTICS & PROBABILITY","Score":null,"Total":0}
引用次数: 1

摘要

集合卡尔曼滤波(EnKF)在大气科学和海洋科学的数据同化方面表现良好。然而,它不能收敛到正确的滤波分布,这使得它不能用于动态系统的不确定性量化。因此,我们在朗格万动力学的框架下重新表述了EnKF,得到了一种新的粒子滤波算法,我们称之为朗格万化EnKF (LEnKF)。LEnKF继承了EnKF的预测分析过程,并使用了随机梯度朗格万动力学(SGLD)的小批量数据。我们证明LEnKF与EnKF一样是一个顺序预处理的SGLD采样器,但它的执行速度被预测分析过程加快了。此外,随着每i阶段迭代次数的增加,LEnKF在2-Wasserstein距离方面收敛到正确的滤波分布。我们使用各种示例来演示LEnKF的性能。LEnKF不仅在状态维数和样本量方面具有可扩展性,而且对于长序列动态数据也倾向于不受样本退化的影响。中国统计:预印本doi:10.5705/ss.202022.0172
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Langevinized Ensemble Kalman Filter for Large-Scale Dynamic Learning
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
Statistica Sinica
Statistica Sinica 数学-统计学与概率论
CiteScore
2.10
自引率
0.00%
发文量
82
审稿时长
10.5 months
期刊介绍: Statistica Sinica aims to meet the needs of statisticians in a rapidly changing world. It provides a forum for the publication of innovative work of high quality in all areas of statistics, including theory, methodology and applications. The journal encourages the development and principled use of statistical methodology that is relevant for society, science and technology.
×
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