低秩矩阵恢复和秩一测量的自适应迭代硬阈值

IF 1.8 2区 数学 Q1 MATHEMATICS
Yu Xia , Likai Zhou
{"title":"低秩矩阵恢复和秩一测量的自适应迭代硬阈值","authors":"Yu Xia ,&nbsp;Likai Zhou","doi":"10.1016/j.jco.2022.101725","DOIUrl":null,"url":null,"abstract":"<div><p>In low-rank matrix recovery, many kinds of measurements fail to meet the standard restricted isometry property (RIP), such as rank-one measurements, that is, <span><math><msub><mrow><mo>[</mo><mi>A</mi><mo>(</mo><mi>X</mi><mo>)</mo><mo>]</mo></mrow><mrow><mi>i</mi></mrow></msub><mo>=</mo><mo>〈</mo><msub><mrow><mi>A</mi></mrow><mrow><mi>i</mi></mrow></msub><mo>,</mo><mi>X</mi><mo>〉</mo></math></span> with <span><math><mtext>rank</mtext><mo>(</mo><msub><mrow><mi>A</mi></mrow><mrow><mi>i</mi></mrow></msub><mo>)</mo><mo>=</mo><mn>1</mn></math></span>, <span><math><mi>i</mi><mo>=</mo><mn>1</mn><mo>,</mo><mo>.</mo><mo>.</mo><mo>.</mo><mo>,</mo><mi>m</mi></math></span><span>. Historical iterative hard thresholding sequence for low-rank matrix recovery and rank-one measurements was taken as </span><span><math><msup><mrow><mi>X</mi></mrow><mrow><mi>n</mi><mo>+</mo><mn>1</mn></mrow></msup><mo>=</mo><msub><mrow><mi>P</mi></mrow><mrow><mi>s</mi></mrow></msub><mo>(</mo><msup><mrow><mi>X</mi></mrow><mrow><mi>n</mi></mrow></msup><mo>−</mo><msub><mrow><mi>μ</mi></mrow><mrow><mi>n</mi></mrow></msub><msub><mrow><mi>P</mi></mrow><mrow><mi>t</mi></mrow></msub><mo>(</mo><msup><mrow><mi>A</mi></mrow><mrow><mo>⁎</mo></mrow></msup><mtext>sign</mtext><mo>(</mo><mi>A</mi><mo>(</mo><msup><mrow><mi>X</mi></mrow><mrow><mi>n</mi></mrow></msup><mo>)</mo><mo>−</mo><mi>y</mi><mo>)</mo><mo>)</mo><mo>)</mo></math></span>, which introduced the “tail” and “head” approximations <span><math><msub><mrow><mi>P</mi></mrow><mrow><mi>s</mi></mrow></msub></math></span> and <span><math><msub><mrow><mi>P</mi></mrow><mrow><mi>t</mi></mrow></msub></math></span>, respectively. In this paper, we remove the term <span><math><msub><mrow><mi>P</mi></mrow><mrow><mi>t</mi></mrow></msub></math></span><span> and provide a new iterative hard thresholding algorithm with adaptive step size (abbreviated as AIHT). The linear convergence analysis and stability results on AIHT are established under the </span><span><math><msub><mrow><mi>ℓ</mi></mrow><mrow><mn>1</mn></mrow></msub><mo>/</mo><msub><mrow><mi>ℓ</mi></mrow><mrow><mn>2</mn></mrow></msub></math></span><span>-RIP. Particularly, we discuss the rank-one Gaussian measurements under the tight upper and lower bounds on </span><span><math><mi>E</mi><msub><mrow><mo>‖</mo><mi>A</mi><mo>(</mo><mi>X</mi><mo>)</mo><mo>‖</mo></mrow><mrow><mn>1</mn></mrow></msub></math></span>, and provide better convergence rate and sampling complexity. Besides, several empirical experiments are provided to show that AIHT performs better than the historical rank-one iterative hard thresholding method.</p></div>","PeriodicalId":50227,"journal":{"name":"Journal of Complexity","volume":"76 ","pages":"Article 101725"},"PeriodicalIF":1.8000,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Adaptive iterative hard thresholding for low-rank matrix recovery and rank-one measurements\",\"authors\":\"Yu Xia ,&nbsp;Likai Zhou\",\"doi\":\"10.1016/j.jco.2022.101725\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>In low-rank matrix recovery, many kinds of measurements fail to meet the standard restricted isometry property (RIP), such as rank-one measurements, that is, <span><math><msub><mrow><mo>[</mo><mi>A</mi><mo>(</mo><mi>X</mi><mo>)</mo><mo>]</mo></mrow><mrow><mi>i</mi></mrow></msub><mo>=</mo><mo>〈</mo><msub><mrow><mi>A</mi></mrow><mrow><mi>i</mi></mrow></msub><mo>,</mo><mi>X</mi><mo>〉</mo></math></span> with <span><math><mtext>rank</mtext><mo>(</mo><msub><mrow><mi>A</mi></mrow><mrow><mi>i</mi></mrow></msub><mo>)</mo><mo>=</mo><mn>1</mn></math></span>, <span><math><mi>i</mi><mo>=</mo><mn>1</mn><mo>,</mo><mo>.</mo><mo>.</mo><mo>.</mo><mo>,</mo><mi>m</mi></math></span><span>. Historical iterative hard thresholding sequence for low-rank matrix recovery and rank-one measurements was taken as </span><span><math><msup><mrow><mi>X</mi></mrow><mrow><mi>n</mi><mo>+</mo><mn>1</mn></mrow></msup><mo>=</mo><msub><mrow><mi>P</mi></mrow><mrow><mi>s</mi></mrow></msub><mo>(</mo><msup><mrow><mi>X</mi></mrow><mrow><mi>n</mi></mrow></msup><mo>−</mo><msub><mrow><mi>μ</mi></mrow><mrow><mi>n</mi></mrow></msub><msub><mrow><mi>P</mi></mrow><mrow><mi>t</mi></mrow></msub><mo>(</mo><msup><mrow><mi>A</mi></mrow><mrow><mo>⁎</mo></mrow></msup><mtext>sign</mtext><mo>(</mo><mi>A</mi><mo>(</mo><msup><mrow><mi>X</mi></mrow><mrow><mi>n</mi></mrow></msup><mo>)</mo><mo>−</mo><mi>y</mi><mo>)</mo><mo>)</mo><mo>)</mo></math></span>, which introduced the “tail” and “head” approximations <span><math><msub><mrow><mi>P</mi></mrow><mrow><mi>s</mi></mrow></msub></math></span> and <span><math><msub><mrow><mi>P</mi></mrow><mrow><mi>t</mi></mrow></msub></math></span>, respectively. In this paper, we remove the term <span><math><msub><mrow><mi>P</mi></mrow><mrow><mi>t</mi></mrow></msub></math></span><span> and provide a new iterative hard thresholding algorithm with adaptive step size (abbreviated as AIHT). The linear convergence analysis and stability results on AIHT are established under the </span><span><math><msub><mrow><mi>ℓ</mi></mrow><mrow><mn>1</mn></mrow></msub><mo>/</mo><msub><mrow><mi>ℓ</mi></mrow><mrow><mn>2</mn></mrow></msub></math></span><span>-RIP. Particularly, we discuss the rank-one Gaussian measurements under the tight upper and lower bounds on </span><span><math><mi>E</mi><msub><mrow><mo>‖</mo><mi>A</mi><mo>(</mo><mi>X</mi><mo>)</mo><mo>‖</mo></mrow><mrow><mn>1</mn></mrow></msub></math></span>, and provide better convergence rate and sampling complexity. Besides, several empirical experiments are provided to show that AIHT performs better than the historical rank-one iterative hard thresholding method.</p></div>\",\"PeriodicalId\":50227,\"journal\":{\"name\":\"Journal of Complexity\",\"volume\":\"76 \",\"pages\":\"Article 101725\"},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2023-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Complexity\",\"FirstCategoryId\":\"100\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0885064X22000905\",\"RegionNum\":2,\"RegionCategory\":\"数学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MATHEMATICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Complexity","FirstCategoryId":"100","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0885064X22000905","RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATHEMATICS","Score":null,"Total":0}
引用次数: 0

摘要

在低秩矩阵恢复中,有多种测量值不满足标准的受限等距性质(RIP),如秩一测量值,即[A(X)]i= < Ai,X >与秩(Ai)=1, i=1,…,m。低秩矩阵恢复和秩一测量的历史迭代硬阈值序列为Xn+1=Ps(Xn−μnPt(A sign(A(Xn)−y)))),分别引入了“尾”近似和“头”近似Ps和Pt。在本文中,我们去掉了Pt项,提出了一种新的自适应步长迭代硬阈值算法(简称AIHT)。在1/ 2-RIP条件下,建立了AIHT的线性收敛分析和稳定性结果。特别地,我们讨论了E‖A(X)‖1紧上界和下界下的秩一高斯测量,并提供了更好的收敛速率和采样复杂度。此外,还提供了一些经验实验,表明AIHT优于历史秩一迭代硬阈值法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Adaptive iterative hard thresholding for low-rank matrix recovery and rank-one measurements

In low-rank matrix recovery, many kinds of measurements fail to meet the standard restricted isometry property (RIP), such as rank-one measurements, that is, [A(X)]i=Ai,X with rank(Ai)=1, i=1,...,m. Historical iterative hard thresholding sequence for low-rank matrix recovery and rank-one measurements was taken as Xn+1=Ps(XnμnPt(Asign(A(Xn)y))), which introduced the “tail” and “head” approximations Ps and Pt, respectively. In this paper, we remove the term Pt and provide a new iterative hard thresholding algorithm with adaptive step size (abbreviated as AIHT). The linear convergence analysis and stability results on AIHT are established under the 1/2-RIP. Particularly, we discuss the rank-one Gaussian measurements under the tight upper and lower bounds on EA(X)1, and provide better convergence rate and sampling complexity. Besides, several empirical experiments are provided to show that AIHT performs better than the historical rank-one iterative hard thresholding method.

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
Journal of Complexity
Journal of Complexity 工程技术-计算机:理论方法
CiteScore
3.10
自引率
17.60%
发文量
57
审稿时长
>12 weeks
期刊介绍: The multidisciplinary Journal of Complexity publishes original research papers that contain substantial mathematical results on complexity as broadly conceived. Outstanding review papers will also be published. In the area of computational complexity, the focus is on complexity over the reals, with the emphasis on lower bounds and optimal algorithms. The Journal of Complexity also publishes articles that provide major new algorithms or make important progress on upper bounds. Other models of computation, such as the Turing machine model, are also of interest. Computational complexity results in a wide variety of areas are solicited. Areas Include: • Approximation theory • Biomedical computing • Compressed computing and sensing • Computational finance • Computational number theory • Computational stochastics • Control theory • Cryptography • Design of experiments • Differential equations • Discrete problems • Distributed and parallel computation • High and infinite-dimensional problems • Information-based complexity • Inverse and ill-posed problems • Machine learning • Markov chain Monte Carlo • Monte Carlo and quasi-Monte Carlo • Multivariate integration and approximation • Noisy data • Nonlinear and algebraic equations • Numerical analysis • Operator equations • Optimization • Quantum computing • Scientific computation • Tractability of multivariate problems • Vision and image understanding.
×
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