{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/99320"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/99320","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Nuclear norm penalized LAD estimator for low rank matrix recovery","abstract":"In the thesis we propose a novel method for low rank matrix recovery. We study the framework using absolute deviation loss function and nuclear penalty. While nuclear norm penalty is widely utilized heuristic method for shrinkage to low rank solution, the absolute deviation loss function is rarely studied. We establish an near oracle optimal recovery bound and gave a proof using E-net covering argument under certain restricted isometry and restricted eigenvalue assumptions. The estimator is able to recover the underlying matrix with high probability with limited observations that the number of observation is more than the degree of freedom but less than a power of dimension. Our estimator has two advantages. First the theoretical tuning parameter does not depends on the knowledge of the noise level, and the bound can be derived even when noises have fatter tails than normal distribution. The second advantage is that absolute deviation loss function is robust compared with the popular square loss function.","abstract_html":"In the thesis we propose a novel method for low rank matrix recovery. We study the framework using absolute deviation loss function and nuclear penalty. While nuclear norm penalty is widely utilized heuristic method for shrinkage to low rank solution, the absolute deviation loss function is rarely studied. We establish an near oracle optimal recovery bound and gave a proof using E-net covering argument under certain restricted isometry and restricted eigenvalue assumptions. The estimator is able to recover the underlying matrix with high probability with limited observations that the number of observation is more than the degree of freedom but less than a power of dimension. Our estimator has two advantages. First the theoretical tuning parameter does not depends on the knowledge of the noise level, and the bound can be derived even when noises have fatter tails than normal distribution. The second advantage is that absolute deviation loss function is robust compared with the popular square loss function.","abstract_has_math":false,"creators":["Wei, Wenzhe"],"institution":"Massachusetts Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Mathematics.","school":null,"contributors":[],"advisors":["Lie Wang."],"committee_chairs":[],"committee_members":[],"year":2015,"date_issued":"2015","date_published":"2015","updated_at":"2026-07-22T22:21:22Z","subjects":["Mathematics."],"languages":["eng"],"rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1721.1/99320","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Lie Wang."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Mathematics."]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Department of Mathematics."]},{"key":"dc:creator","label":"Author","values":["Wei, Wenzhe"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2015-10-14T15:05:29Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2015-10-14T15:05:29Z"]},{"key":"dc:date.issued","label":"Date","values":["2015"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Mathematics."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1721.1/99320"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis: Ph. D., Massachusetts Institute of Technology, Department of Mathematics, 2015.","Cataloged from PDF version of thesis.","Includes bibliographical references (pages 45-47)."]},{"key":"dc:description.abstract","label":"Abstract","values":["In the thesis we propose a novel method for low rank matrix recovery. We study the framework using absolute deviation loss function and nuclear penalty. While nuclear norm penalty is widely utilized heuristic method for shrinkage to low rank solution, the absolute deviation loss function is rarely studied. We establish an near oracle optimal recovery bound and gave a proof using E-net covering argument under certain restricted isometry and restricted eigenvalue assumptions. The estimator is able to recover the underlying matrix with high probability with limited observations that the number of observation is more than the degree of freedom but less than a power of dimension. Our estimator has two advantages. First the theoretical tuning parameter does not depends on the knowledge of the noise level, and the bound can be derived even when noises have fatter tails than normal distribution. The second advantage is that absolute deviation loss function is robust compared with the popular square loss function."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph. D."]},{"key":"dc:title","label":"Title","values":["Nuclear norm penalized LAD estimator for low rank matrix recovery"]}]}],"canonical_facts":{"dc:contributor.advisor":["Lie Wang."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Mathematics."],"dc:contributor.other":["Massachusetts Institute of Technology. Department of Mathematics."],"dc:creator":["Wei, Wenzhe"],"dc:date.accessioned":["2015-10-14T15:05:29Z"],"dc:date.available":["2015-10-14T15:05:29Z"],"dc:date.issued":["2015"],"dc:description":["Thesis: Ph. D., Massachusetts Institute of Technology, Department of Mathematics, 2015.","Cataloged from PDF version of thesis.","Includes bibliographical references (pages 45-47)."],"dc:description.abstract":["In the thesis we propose a novel method for low rank matrix recovery. We study the framework using absolute deviation loss function and nuclear penalty. While nuclear norm penalty is widely utilized heuristic method for shrinkage to low rank solution, the absolute deviation loss function is rarely studied. We establish an near oracle optimal recovery bound and gave a proof using E-net covering argument under certain restricted isometry and restricted eigenvalue assumptions. The estimator is able to recover the underlying matrix with high probability with limited observations that the number of observation is more than the degree of freedom but less than a power of dimension. Our estimator has two advantages. First the theoretical tuning parameter does not depends on the knowledge of the noise level, and the bound can be derived even when noises have fatter tails than normal distribution. The second advantage is that absolute deviation loss function is robust compared with the popular square loss function."],"dc:description.degree":["Ph. D."],"dc:identifier.uri":["http://hdl.handle.net/1721.1/99320"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Mathematics."],"dc:title":["Nuclear norm penalized LAD estimator for low rank matrix recovery"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:21:22Z"}