{"title":"相干低管阶张量补全","authors":"Andong Wang, Zhong Jin, Xiangrui Li","doi":"10.1109/ACPR.2017.66","DOIUrl":null,"url":null,"abstract":"The sufficient condition of exact completion of coherent low-tubal-rank tensors is studied in this paper. When the leveraged sampling strategy is adopted instead of the uniform sampling strategy, it can be shown that any 3-D tensor of size n_1 × n_2 × n_3 having tubal-rank r can be exactly recovered using tubal nuclear norm minimization with high probability when the number of observed entries is of order O(max{n_1, n_2}n_3r log^2((n_1+n_2)n_3)). This result removes the tensor incoherence parameter μ_0 in the sample complexity O(μ_0 max{n_1, n_2}n_3r log((n_1+n_2)n_3)) of uniform sampling strategy and can significantly reduce the number of observations for a tensor with The sufficient condition of exact completion of coherent low-tubal-rank tensors is studied in this paper. When the leveraged sampling strategy is adopted instead of the uniform sampling strategy, it can be shown that any 3-D tensor of size n1 x n2 x n3 having tubal-rank r can be exactly recovered using tubal nuclear norm minimization with high probability when the number of observed entries is of order O(max{n1, n2}n3r log2((n1+n2)n3)). This result removes the tensor incoherence parameter µ0 in the sample complexity O(µ0 max{n1, n2}n3r log((n1+n2)n3)) of uniform sampling strategy and can significantly reduce the number of observations for a tensor with large µ0.","PeriodicalId":426561,"journal":{"name":"2017 4th IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Coherent Low-tubal-Rank Tensor Completion\",\"authors\":\"Andong Wang, Zhong Jin, Xiangrui Li\",\"doi\":\"10.1109/ACPR.2017.66\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The sufficient condition of exact completion of coherent low-tubal-rank tensors is studied in this paper. When the leveraged sampling strategy is adopted instead of the uniform sampling strategy, it can be shown that any 3-D tensor of size n_1 × n_2 × n_3 having tubal-rank r can be exactly recovered using tubal nuclear norm minimization with high probability when the number of observed entries is of order O(max{n_1, n_2}n_3r log^2((n_1+n_2)n_3)). This result removes the tensor incoherence parameter μ_0 in the sample complexity O(μ_0 max{n_1, n_2}n_3r log((n_1+n_2)n_3)) of uniform sampling strategy and can significantly reduce the number of observations for a tensor with The sufficient condition of exact completion of coherent low-tubal-rank tensors is studied in this paper. When the leveraged sampling strategy is adopted instead of the uniform sampling strategy, it can be shown that any 3-D tensor of size n1 x n2 x n3 having tubal-rank r can be exactly recovered using tubal nuclear norm minimization with high probability when the number of observed entries is of order O(max{n1, n2}n3r log2((n1+n2)n3)). This result removes the tensor incoherence parameter µ0 in the sample complexity O(µ0 max{n1, n2}n3r log((n1+n2)n3)) of uniform sampling strategy and can significantly reduce the number of observations for a tensor with large µ0.\",\"PeriodicalId\":426561,\"journal\":{\"name\":\"2017 4th IAPR Asian Conference on Pattern Recognition (ACPR)\",\"volume\":\"10 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 4th IAPR Asian Conference on Pattern Recognition (ACPR)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ACPR.2017.66\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 4th IAPR Asian Conference on Pattern Recognition (ACPR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ACPR.2017.66","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
研究了相干低管秩张量精确完备的充分条件。当采用杠杆采样策略代替均匀采样策略时,可以证明当观测项数为O阶(max{n_1, n_2}n_3r log^2((n_1+n_2)n_3))时,任何尺寸为n_1 × n_2 × n_3的管状秩为r的三维张量都可以用管状核范数最小化方法高概率精确恢复。该结果消除了均匀采样策略的样本复杂度O(μ_0 max{n_1, n_2}n_3r log((n_1+n_2)n_3))中的张量不相干参数μ_0,可以显著减少张量的观测次数,并研究了相干低管秩张量精确完备的充分条件。当采用杠杆采样策略代替均匀采样策略时,可以证明当观测到的项数为O阶(max{n1, n2}n3r log2((n1+n2)n3))时,任何大小为n1 x n2 x n3且管状秩为r的三维张量都可以用管状核范数最小化高概率精确恢复。该结果消除了均匀采样策略的样本复杂度O(µ0 max{n1, n2}n3r log((n1+n2)n3))中的张量不相干参数µ0,可以显著减少大µ0张量的观测次数。
The sufficient condition of exact completion of coherent low-tubal-rank tensors is studied in this paper. When the leveraged sampling strategy is adopted instead of the uniform sampling strategy, it can be shown that any 3-D tensor of size n_1 × n_2 × n_3 having tubal-rank r can be exactly recovered using tubal nuclear norm minimization with high probability when the number of observed entries is of order O(max{n_1, n_2}n_3r log^2((n_1+n_2)n_3)). This result removes the tensor incoherence parameter μ_0 in the sample complexity O(μ_0 max{n_1, n_2}n_3r log((n_1+n_2)n_3)) of uniform sampling strategy and can significantly reduce the number of observations for a tensor with The sufficient condition of exact completion of coherent low-tubal-rank tensors is studied in this paper. When the leveraged sampling strategy is adopted instead of the uniform sampling strategy, it can be shown that any 3-D tensor of size n1 x n2 x n3 having tubal-rank r can be exactly recovered using tubal nuclear norm minimization with high probability when the number of observed entries is of order O(max{n1, n2}n3r log2((n1+n2)n3)). This result removes the tensor incoherence parameter µ0 in the sample complexity O(µ0 max{n1, n2}n3r log((n1+n2)n3)) of uniform sampling strategy and can significantly reduce the number of observations for a tensor with large µ0.