Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence
The task of recovering a low-rank matrix from its noisy linear measurements plays a central role in computational science. Smooth formulations of the problem often exhibit an undesirable phenomenon: the condition number, classically defined, scales poorly with the dimension of the ambient space. In...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
22.04.2019
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The task of recovering a low-rank matrix from its noisy linear measurements plays a central role in computational science. Smooth formulations of the problem often exhibit an undesirable phenomenon: the condition number, classically defined, scales poorly with the dimension of the ambient space. In contrast, we here show that in a variety of concrete circumstances, nonsmooth penalty formulations do not suffer from the same type of ill-conditioning. Consequently, standard algorithms for nonsmooth optimization, such as subgradient and prox-linear methods, converge at a rapid dimension-independent rate when initialized within constant relative error of the solution. Moreover, nonsmooth formulations are naturally robust against outliers. Our framework subsumes such important computational tasks as phase retrieval, blind deconvolution, quadratic sensing, matrix completion, and robust PCA. Numerical experiments on these problems illustrate the benefits of the proposed approach. |
---|---|
AbstractList | The task of recovering a low-rank matrix from its noisy linear measurements plays a central role in computational science. Smooth formulations of the problem often exhibit an undesirable phenomenon: the condition number, classically defined, scales poorly with the dimension of the ambient space. In contrast, we here show that in a variety of concrete circumstances, nonsmooth penalty formulations do not suffer from the same type of ill-conditioning. Consequently, standard algorithms for nonsmooth optimization, such as subgradient and prox-linear methods, converge at a rapid dimension-independent rate when initialized within constant relative error of the solution. Moreover, nonsmooth formulations are naturally robust against outliers. Our framework subsumes such important computational tasks as phase retrieval, blind deconvolution, quadratic sensing, matrix completion, and robust PCA. Numerical experiments on these problems illustrate the benefits of the proposed approach. |
Author | Chen, Yudong Charisopoulos, Vasileios Díaz, Mateo Ding, Lijun Drusvyatskiy, Dmitriy Davis, Damek |
Author_xml | – sequence: 1 givenname: Vasileios surname: Charisopoulos fullname: Charisopoulos, Vasileios – sequence: 2 givenname: Yudong surname: Chen fullname: Chen, Yudong – sequence: 3 givenname: Damek surname: Davis fullname: Davis, Damek – sequence: 4 givenname: Mateo surname: Díaz fullname: Díaz, Mateo – sequence: 5 givenname: Lijun surname: Ding fullname: Ding, Lijun – sequence: 6 givenname: Dmitriy surname: Drusvyatskiy fullname: Drusvyatskiy, Dmitriy |
BookMark | eNqNjMsKwjAURIMoWLX_EHBdqIl94FYUFy7dSgltrLfae2uSWvXrreIHuBrOnGEmbIiEesA8IeUiSJdCjJlvbRWGoYgTEUXSY8c9dYFReOG1cgYe3Oic7to8eQfuzHOqG7LgNKfGQQ0v5YBwxUuiopdYwIcBS66w4EY18K37g1JjrmdsdFJXq_1fTtl8uzmsd0Fj6NZq67KKWoO9yoRYyFjKNInkf6s3KrxGrw |
ContentType | Paper |
Copyright | 2019. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2019. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central SciTech Premium Collection (Proquest) (PQ_SDU_P3) ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_22136338753 |
IEDL.DBID | 8FG |
IngestDate | Mon Oct 07 13:05:17 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_22136338753 |
OpenAccessLink | https://www.proquest.com/docview/2213633875/abstract/?pq-origsite=%requestingapplication% |
PQID | 2213633875 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_2213633875 |
PublicationCentury | 2000 |
PublicationDate | 20190422 |
PublicationDateYYYYMMDD | 2019-04-22 |
PublicationDate_xml | – month: 04 year: 2019 text: 20190422 day: 22 |
PublicationDecade | 2010 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2019 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.2078204 |
SecondaryResourceType | preprint |
Snippet | The task of recovering a low-rank matrix from its noisy linear measurements plays a central role in computational science. Smooth formulations of the problem... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Algorithms Computation Convergence Formulations Ill-conditioned problems (mathematics) Mathematical analysis Matrix methods Optimization Outliers (statistics) Phase retrieval Robustness (mathematics) |
Title | Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence |
URI | https://www.proquest.com/docview/2213633875/abstract/ |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dS8MwED_miuCbn_gxR0BfQ23SNp0vgtI6xI0hCnuRkaSt-LC26-rXi3-7ua7VB2GPSSAk4XKX_O5-dwDn3BtwmfqcBvJCU3egY6qYSKnvaSE187VUSHAejf3hk3s39aYdGLZcGAyrbHVirajjXCNGbjPmcN_8p4RnS4UogK7sq2JBsX4U-lmbYhobYDmYEw8549HtL9rCfGHezvyfwq2tSLQN1kQWSbkDnSTbhc06-FIv9-D5Pv-gWDydzDFh_ifBX6oRsS-CKCnBqG8MrUpIbu73vCFOXpKXPI_NIPqcV6AqkVlMSlm81t3vK15lsg9nUfh4M6TtmmaN_Cxnf7vlB9DN8iw5BOIKL-aBclyNScBEGiBxlAuulUiVsbVH0Fs30_H64RPYMo-B2lPCWA-6VfmWnBqDW6l-fZZ9sK7D8eTBtEbf4Q9Zoo2j |
link.rule.ids | 786,790,12792,21416,33408,33779,43635,43840 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1bS8MwFD5oi-ibV7xMDehr0CVt0vkiKBtVuzJkwl6kpGkrPqyt7bz9e3O6Th-EveZASMLJuXznBnDO3R5XmeDUU5eaOj2d0JjJjApXS6WZ0CrGAudhKPwn537iTlrArW7TKhcysRHUSaERI79grMuF8aeke12-UZwahdHVdoTGKtgON66KBfZNPxw9_qIsTEhjM_N_grbRHoNNsEeqTKstWEnzbVhrki51vQPPQfFJcWg6mWKj_C-C3qlhrW-C6CjBbG9MqUpJYf71tC2YvCIvRZEYIsaa52AqUXlCKlW-Nssf83rKdBfOBv3xrU8XZ4pavqmjv1vyPbDyIk_3gTjSTbgXdx2Nzb9k5mHBKJdcxzKLjY49gM6ynQ6Xk09h3R8Pgyi4Cx-OYMMYBE20hLEOWLPqPT02SncWn7Qv-wP37Its |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Low-rank+matrix+recovery+with+composite+optimization%3A+good+conditioning+and+rapid+convergence&rft.jtitle=arXiv.org&rft.au=Charisopoulos%2C+Vasileios&rft.au=Chen%2C+Yudong&rft.au=Davis%2C+Damek&rft.au=D%C3%ADaz%2C+Mateo&rft.date=2019-04-22&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |