[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-513107-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-513107-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","tensor-completion-via-monotone-inclusion-generalized-low-rank-priors-meet-deep-denoisers","Tensor Completion via Monotone Inclusion - Generalized Low-Rank Priors Meet Deep Denoisers","","Missing entries in multi-dimensional data hinder downstream analysis across many real-world applications. Tensors offer a natural modeling framework for color images, multi-/hyper-spectral images, color videos, and spatio-temporal traffic signals, motivating tensor completion. Existing methods combine global low-rank priors with plug-and-play denoisers but often depend on empirical convergence or unrealistic proximal assumptions. This work proposes a monotone-inclusion-based framework with generalized low-rank priors and deep denoising operators, yielding the GTCTV-DPC algorithm with global convergence guarantees and improved performance, especially under low sampling rates.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/tensor-completion-via-monotone-inclusion-generalized-low-rank-priors-meet-deep-denoisers/513107/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/tensor-completion-via-monotone-inclusion-generalized-low-rank-priors-meet-deep-denoisers/513107.png","ImageObject",300,407,{"name":42,"@type":43},"404brain","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-07","2026-10-06",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",6,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the paper address?","Question",{"text":63,"@type":64},"The paper addresses tensor completion when entries are missing, i.e., recovering an underlying tensor from partially observed data.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Why do prior plug-and-play denoising approaches have limitations?",{"text":68,"@type":64},"They often rely on empirical convergence alone or assume that deep denoisers act as proximal operators of implicit regularizers, which generally does not hold.",{"name":70,"@type":61,"acceptedAnswer":71},"How does the proposed method handle deep denoisers?",{"text":72,"@type":64},"Deep denoisers are treated as general operators within a monotone inclusion paradigm, rather than requiring restrictive optimization-based proximal assumptions.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},513107,1791460780,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,105,110,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":111,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":33,"preview_urls":146},1099529839291,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","Tensor Completion via Monotone Inclusion: Generalized Low-Rank Priors Meet Deep Denoisers  \nPeng Chen* , Deliang Wei* , Jiale Yao, and Fang Li  \narXiv :2510 . 12425v2 [math .OC] 31 Oct 2025  \nAbstract—Missing entries in multi-dimensional data pose significant challenges for downstream analysis across diverse realworld applications. These data are naturally represented as tensors, and recent completion methods integrating global lowrank priors with plug-and-play denoisers have demonstrated strong empirical performance. However, these approaches often rely on empirical convergence alone or unrealistic assumptions, such as deep denoisers acting as proximal operators of implicit regularizers, which generally does not hold. To address these limitations, we propose a novel tensor completion framework grounded in the monotone inclusion paradigm. Within this framework, deep denoisers are treated as general operators that require far fewer restrictions than in classical optimization-based formulations. To better capture holistic structure, we further incorporate generalized low-rank priors with weakly convex penalties. Building upon the Davis–Yin splitting scheme, we develop the GTCTV-DPC algorithm and rigorously establish its global convergence. Extensive experiments demonstrate that GTCTV-DPC consistently outperforms existing methods in both quantitative metrics and visual quality, particularly at low sampling rates. For instance, at a sampling rate of 0.05 for multi-dimensional image completion, GTCTV-DPC achieves an average mean peak-signal-to-noise ratio (MPSNR) that surpasses the second-best method by 0.717 dB, and 0.649 dB for multispectral images, and color videos, respectively.  \nIndex Terms—Tensor completion, monotone inclusion, generalized low-rank priors, deep pseudo-contractive denoisers  \nI. INTRODUCTION  \nTHE presence of missing entries in data, often resulting  \nfrom sensor malfunctions, occlusions, or transmission errors, poses a persistent challenge in data analysis [1] . Tensors, as multi-dimensional arrays, provide a versatile framework for modeling diverse real-world datasets, such as color images [2], multi-/hyper-spectral images (MSI/HSI) [3], color videos [4], and spatio-temporal traffic data [5] . Consequently, tensor completion has become a pivotal research area, attracting significant attention within the scientific community [6]–[8] . In this work, we address tensor completion from highly incomplete observations by developing a unified framework grounded in the monotone inclusion paradigm, which integrates generalized low-rank priors with deep denoising priors.  \nThe general problem of missing entries in tensor data can be formulated as Y = PΩ (X), where Y ∈ Rn1 ×n2 × · ·· ×nN  \ndenotes the observed data with missing entries, X is the * These authors contributed equally to this work.  \nPeng Chen, Jiale Yao, and Fang Li are with the School of Mathematical Sciences, East China Normal University, Shanghai 200241, China (email: [pengchen2209@stu.ecnu.edu.cn](pengchen2209@stu.ecnu.edu.cn); [52285500019@stu.ecnu.edu.cn](52285500019@stu.ecnu.edu.cn); [fli@math.ecnu.edu.cn](fli@math.ecnu.edu.cn)) .  \nDeliang Wei is with the Data Science and AI institute, Johns Hopkins University, Baltimore, MD 21218, America (e-mail: [dwei12@jh.edu](dwei12@jh.edu)).  \nunderlying complete tensor, Ω is the index set of observed entries, and PΩ is the projection operator that preserves entries in Ω and sets all others to zero:  \n[PΩ (X)]i1 i2...iN = (X0i1 i2...iN h(1rw, ii2s,e.. .., iN ) ∈ Ω ,  \nTo recover X from Y, a constrained optimization framework is commonly employed:  \nmin R(X) s.t. PΩ (X) = PΩ (Y) .  \nX  \nHere, R (·) is a regularizer that encodes the intrinsic structural properties of X. In the following, we review related works in two principal directions for designing R.  \nA. Related works  \n1) Low-rank based methods: Low-rankness has emerged asa dominant prior for designing R, as it facilitates the extraction of essential st","cbCainDLYo9Djtws","https://ap.wps.com/l/cbCainDLYo9Djtws","pdf",44807017,14,"English","# Introduction\n## Related works\n# Problem formulation\n# Low-rank based methods","[{\"question\":\"What problem does the paper address?\",\"answer\":\"The paper addresses tensor completion when entries are missing, i.e., recovering an underlying tensor from partially observed data.\"},{\"question\":\"Why do prior plug-and-play denoising approaches have limitations?\",\"answer\":\"They often rely on empirical convergence alone or assume that deep denoisers act as proximal operators of implicit regularizers, which generally does not hold.\"},{\"question\":\"How does the proposed method handle deep denoisers?\",\"answer\":\"Deep denoisers are treated as general operators within a monotone inclusion paradigm, rather than requiring restrictive optimization-based proximal assumptions.\"}]","Tensor Completion via Monotone Inclusion - Generalized Low-Rank Priors Meet Deep Denoisers | PDF",1791280191,35,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/cd6a8ce73fae71b05bf7e999f034be45.webp",983,1272,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/08d454660ac1b1bbfd2bc4c768a0b7aa.webp",982,1270,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/c67d0993c43c56e5b568358367e7ab91.webp",981,1269,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/663f95f4c2f1857419d57fb1ba5e9948.webp",980,1268]