Deep Unfolded Tensor Robust PCA with Self-supervised Learning

Tensor robust principal component analysis (RPCA), which seeks to separate a low-rank tensor from its sparse corruptions, has been crucial in data science and machine learning where tensor structures are becoming more prevalent. While powerful, existing tensor RPCA algorithms can be difficult to use...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dong, Harry, Shah, Megna, Donegan, Sean, Chi, Yuejie
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Dong, Harry
Shah, Megna
Donegan, Sean
Chi, Yuejie
description Tensor robust principal component analysis (RPCA), which seeks to separate a low-rank tensor from its sparse corruptions, has been crucial in data science and machine learning where tensor structures are becoming more prevalent. While powerful, existing tensor RPCA algorithms can be difficult to use in practice, as their performance can be sensitive to the choice of additional hyperparameters, which are not straightforward to tune. In this paper, we describe a fast and simple self-supervised model for tensor RPCA using deep unfolding by only learning four hyperparameters. Despite its simplicity, our model expunges the need for ground truth labels while maintaining competitive or even greater performance compared to supervised deep unfolding. Furthermore, our model is capable of operating in extreme data-starved scenarios. We demonstrate these claims on a mix of synthetic data and real-world tasks, comparing performance against previously studied supervised deep unfolding methods and Bayesian optimization baselines.
doi_str_mv 10.48550/arxiv.2212.11346
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2212_11346</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2212_11346</sourcerecordid><originalsourceid>FETCH-LOGICAL-a676-a48999861eeb043291ba30edf566007600beac3c003889dec24c410bae9803173</originalsourceid><addsrcrecordid>eNotj7tOxDAURN1QoIUPoMI_kHD9iGMXFKvwlCKBINTRdXIDlkIS2bsL_D27C8VomtHRHMYuBOTaFgVcYfwOu1xKIXMhlDan7PqGaOFv0zCPPfW8oSnNkb_Mfps2_Lla86-w-eCvNA5Z2i4UdyHtZzVhnML0fsZOBhwTnf_3ijV3t031kNVP94_Vus7QlCZDbZ1z1ggiD1pJJzwqoH4ojAEo9_GEneoAlLWup07qTgvwSM6CEqVascs_7PF_u8TwifGnPXi0Rw_1C4QXQV4</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Deep Unfolded Tensor Robust PCA with Self-supervised Learning</title><source>arXiv.org</source><creator>Dong, Harry ; Shah, Megna ; Donegan, Sean ; Chi, Yuejie</creator><creatorcontrib>Dong, Harry ; Shah, Megna ; Donegan, Sean ; Chi, Yuejie</creatorcontrib><description>Tensor robust principal component analysis (RPCA), which seeks to separate a low-rank tensor from its sparse corruptions, has been crucial in data science and machine learning where tensor structures are becoming more prevalent. While powerful, existing tensor RPCA algorithms can be difficult to use in practice, as their performance can be sensitive to the choice of additional hyperparameters, which are not straightforward to tune. In this paper, we describe a fast and simple self-supervised model for tensor RPCA using deep unfolding by only learning four hyperparameters. Despite its simplicity, our model expunges the need for ground truth labels while maintaining competitive or even greater performance compared to supervised deep unfolding. Furthermore, our model is capable of operating in extreme data-starved scenarios. We demonstrate these claims on a mix of synthetic data and real-world tasks, comparing performance against previously studied supervised deep unfolding methods and Bayesian optimization baselines.</description><identifier>DOI: 10.48550/arxiv.2212.11346</identifier><language>eng</language><subject>Computer Science - Learning ; Statistics - Machine Learning</subject><creationdate>2022-12</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2212.11346$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2212.11346$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Dong, Harry</creatorcontrib><creatorcontrib>Shah, Megna</creatorcontrib><creatorcontrib>Donegan, Sean</creatorcontrib><creatorcontrib>Chi, Yuejie</creatorcontrib><title>Deep Unfolded Tensor Robust PCA with Self-supervised Learning</title><description>Tensor robust principal component analysis (RPCA), which seeks to separate a low-rank tensor from its sparse corruptions, has been crucial in data science and machine learning where tensor structures are becoming more prevalent. While powerful, existing tensor RPCA algorithms can be difficult to use in practice, as their performance can be sensitive to the choice of additional hyperparameters, which are not straightforward to tune. In this paper, we describe a fast and simple self-supervised model for tensor RPCA using deep unfolding by only learning four hyperparameters. Despite its simplicity, our model expunges the need for ground truth labels while maintaining competitive or even greater performance compared to supervised deep unfolding. Furthermore, our model is capable of operating in extreme data-starved scenarios. We demonstrate these claims on a mix of synthetic data and real-world tasks, comparing performance against previously studied supervised deep unfolding methods and Bayesian optimization baselines.</description><subject>Computer Science - Learning</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj7tOxDAURN1QoIUPoMI_kHD9iGMXFKvwlCKBINTRdXIDlkIS2bsL_D27C8VomtHRHMYuBOTaFgVcYfwOu1xKIXMhlDan7PqGaOFv0zCPPfW8oSnNkb_Mfps2_Lla86-w-eCvNA5Z2i4UdyHtZzVhnML0fsZOBhwTnf_3ijV3t031kNVP94_Vus7QlCZDbZ1z1ggiD1pJJzwqoH4ojAEo9_GEneoAlLWup07qTgvwSM6CEqVascs_7PF_u8TwifGnPXi0Rw_1C4QXQV4</recordid><startdate>20221221</startdate><enddate>20221221</enddate><creator>Dong, Harry</creator><creator>Shah, Megna</creator><creator>Donegan, Sean</creator><creator>Chi, Yuejie</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20221221</creationdate><title>Deep Unfolded Tensor Robust PCA with Self-supervised Learning</title><author>Dong, Harry ; Shah, Megna ; Donegan, Sean ; Chi, Yuejie</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a676-a48999861eeb043291ba30edf566007600beac3c003889dec24c410bae9803173</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Learning</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Dong, Harry</creatorcontrib><creatorcontrib>Shah, Megna</creatorcontrib><creatorcontrib>Donegan, Sean</creatorcontrib><creatorcontrib>Chi, Yuejie</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Dong, Harry</au><au>Shah, Megna</au><au>Donegan, Sean</au><au>Chi, Yuejie</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Deep Unfolded Tensor Robust PCA with Self-supervised Learning</atitle><date>2022-12-21</date><risdate>2022</risdate><abstract>Tensor robust principal component analysis (RPCA), which seeks to separate a low-rank tensor from its sparse corruptions, has been crucial in data science and machine learning where tensor structures are becoming more prevalent. While powerful, existing tensor RPCA algorithms can be difficult to use in practice, as their performance can be sensitive to the choice of additional hyperparameters, which are not straightforward to tune. In this paper, we describe a fast and simple self-supervised model for tensor RPCA using deep unfolding by only learning four hyperparameters. Despite its simplicity, our model expunges the need for ground truth labels while maintaining competitive or even greater performance compared to supervised deep unfolding. Furthermore, our model is capable of operating in extreme data-starved scenarios. We demonstrate these claims on a mix of synthetic data and real-world tasks, comparing performance against previously studied supervised deep unfolding methods and Bayesian optimization baselines.</abstract><doi>10.48550/arxiv.2212.11346</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2212.11346
ispartof
issn
language eng
recordid cdi_arxiv_primary_2212_11346
source arXiv.org
subjects Computer Science - Learning
Statistics - Machine Learning
title Deep Unfolded Tensor Robust PCA with Self-supervised Learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T04%3A25%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Deep%20Unfolded%20Tensor%20Robust%20PCA%20with%20Self-supervised%20Learning&rft.au=Dong,%20Harry&rft.date=2022-12-21&rft_id=info:doi/10.48550/arxiv.2212.11346&rft_dat=%3Carxiv_GOX%3E2212_11346%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true