{"id":"https://openalex.org/W4389325865","doi":"https://doi.org/10.48550/arxiv.2312.00386","title":"Local monotone operator learning using non-monotone operators: MnM-MOL","display_name":"Local monotone operator learning using non-monotone operators: MnM-MOL","publication_year":2023,"publication_date":"2023-12-01","ids":{"openalex":"https://openalex.org/W4389325865","doi":"https://doi.org/10.48550/arxiv.2312.00386"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2312.00386","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.00386","pdf_url":"https://arxiv.org/pdf/2312.00386","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2312.00386","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078856547","display_name":"Maneesh John","orcid":"https://orcid.org/0000-0002-1528-7759","observed_orcids":["https://orcid.org/0000-0002-1528-7759"]},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John, Maneesh","raw_affiliation_strings":["Department of Electrical and Computer Engineering at the University of Iowa , Iowa City , IA , 52242 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering at the University of Iowa , Iowa City , IA , 52242 , USA","institution_ids":["https://openalex.org/I126307644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072491757","display_name":"Jyothi Rikhab Chand","orcid":"https://orcid.org/0000-0002-8335-6103","observed_orcids":["https://orcid.org/0000-0002-8335-6103"]},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chand, Jyothi Rikhab","raw_affiliation_strings":["Department of Electrical and Computer Engineering at the University of Iowa , Iowa City , IA , 52242 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering at the University of Iowa , Iowa City , IA , 52242 , USA","institution_ids":["https://openalex.org/I126307644"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072299998","display_name":"Mathews Jacob","orcid":"https://orcid.org/0000-0001-6196-3933","observed_orcids":["https://orcid.org/0000-0001-6196-3933"]},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob, Mathews","raw_affiliation_strings":["Department of Electrical and Computer Engineering at the University of Iowa , Iowa City , IA , 52242 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering at the University of Iowa , Iowa City , IA , 52242 , USA","institution_ids":["https://openalex.org/I126307644"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126307644"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10378","display_name":"Advanced MRI Techniques and Applications","score":0.5565999746322632,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10378","display_name":"Advanced MRI Techniques and Applications","score":0.5565999746322632,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.19820000231266022,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.10830000042915344,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/non-monotone-operators","display_name":"non-monotone operators","score":0.8659999966621399},{"id":"https://openalex.org/keywords/mri-reconstruction","display_name":"MRI reconstruction","score":0.7649999856948853},{"id":"https://openalex.org/keywords/undersampled-mri","display_name":"undersampled MRI","score":0.6800000071525574},{"id":"https://openalex.org/keywords/deep-equilibrium-models","display_name":"deep equilibrium models","score":0.9200000166893005},{"id":"https://openalex.org/keywords/fixed-point-convergence","display_name":"fixed point convergence","score":0.7919999957084656},{"id":"https://openalex.org/keywords/robustness-to-input-perturbations","display_name":"robustness to input perturbations","score":0.878000020980835},{"id":"https://openalex.org/keywords/memory-efficient-training","display_name":"memory-efficient training","score":0.6629999876022339}],"concepts":[{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.7346861362457275},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.637660562992096},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.6207760572433472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.619503378868103},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5680528879165649},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5222876071929932},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49316614866256714},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47804170846939087},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4221898317337036},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.41032516956329346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3259275257587433},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2775718569755554},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2312.00386","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.00386","pdf_url":"https://arxiv.org/pdf/2312.00386","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2312.00386","doi":"https://doi.org/10.48550/arxiv.2312.00386","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.00386","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2312.00386","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.00386","pdf_url":"https://arxiv.org/pdf/2312.00386","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389325865.pdf","grobid_xml":"https://content.openalex.org/works/W4389325865.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4226118383","https://openalex.org/W4401571541","https://openalex.org/W4386352406","https://openalex.org/W4287548791","https://openalex.org/W4323338375","https://openalex.org/W4404745985","https://openalex.org/W4383753104","https://openalex.org/W6965204049","https://openalex.org/W4226193177","https://openalex.org/W4411406281"],"abstract_inverted_index":{"The":[0,117],"recovery":[1],"of":[2,29,48,120,150,153],"magnetic":[3],"resonance":[4],"(MR)":[5],"images":[6],"from":[7],"undersampled":[8],"measurements":[9],"is":[10,123,215,227,235],"a":[11,45,90,169,200],"key":[12],"problem":[13],"that":[14,98,211,224,233,246,255],"has":[15],"seen":[16],"extensive":[17],"research":[18],"in":[19,57,110,132,199],"recent":[20,66],"years.":[21],"Unrolled":[22],"approaches,":[23],"which":[24,183],"rely":[25],"on":[26,93,128,147],"end-to-end":[27],"training":[28],"convolutional":[30],"neural":[31],"network":[32,95],"(CNN)":[33],"blocks":[34],"within":[35],"iterative":[36],"reconstruction":[37],"algorithms,":[38],"offer":[39],"state-of-the-art":[40],"performance.":[41,188],"These":[42],"algorithms":[43],"require":[44,89],"large":[46],"amount":[47],"memory":[49,83],"during":[50,85],"training,":[51],"making":[52],"them":[53],"difficult":[54],"to":[55,74,96,114,124,167,177,186,196,217,219,229,238,251,260,264],"employ":[56],"high-dimensional":[58],"applications.":[59],"Deep":[60],"equilibrium":[61],"(DEQ)":[62],"models":[63],"and":[64,101,157,223,254],"the":[65,76,82,94,99,106,126,129,144,148,151,154,158,164,175,194,204,212,220,225,239,247,256],"monotone":[67,145,170,198],"operator":[68,195],"learning":[69],"(MOL)":[70],"approach":[71,173,257],"were":[72],"introduced":[73],"eliminate":[75],"need":[77],"for":[78],"unrolling,":[79],"thus":[80],"reducing":[81],"demand":[84],"training.":[86],"Both":[87],"approaches":[88],"Lipschitz":[91],"constraint":[92,107,127,146],"ensure":[97],"forward":[100],"backpropagation":[102],"iterations":[103],"converge.":[104],"Unfortunately,":[105],"often":[108],"results":[109,209,244],"reduced":[111],"performance":[112,253],"compared":[113],"unrolled":[115],"methods.":[116],"main":[118],"focus":[119],"this":[121],"work":[122],"relax":[125],"CNN":[130,159,165,176],"block":[131],"two":[133],"different":[134],"ways.":[135],"Inspired":[136],"by":[137],"convex-non-convex":[138],"regularization":[139],"strategies,":[140],"we":[141,191],"now":[142],"impose":[143],"sum":[149],"gradient":[152],"data":[155],"term":[156],"block,":[160],"rather":[161],"than":[162],"constrain":[163],"itself":[166],"be":[168,197],"operator.":[171],"This":[172],"enables":[174],"learn":[178],"possibly":[179],"non-monotone":[180],"score":[181],"functions,":[182],"can":[184],"translate":[185,250],"improved":[187,252],"In":[189],"addition,":[190],"only":[192],"restrict":[193],"local":[201],"neighborhood":[202],"around":[203],"image":[205],"manifold.":[206],"Our":[207,242],"theoretical":[208],"show":[210,245],"proposed":[213],"algorithm":[214],"guaranteed":[216],"converge":[218],"fixed":[221],"point":[222],"solution":[226],"robust":[228],"input":[230,261],"perturbations,":[231],"provided":[232],"it":[234],"initialized":[236],"close":[237],"true":[240],"solution.":[241],"empirical":[243],"relaxed":[248],"constraints":[249],"enjoys":[258],"robustness":[259],"perturbations":[262],"similar":[263],"MOL.":[265]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2023-12-05T00:00:00"}