{"id":"https://openalex.org/W4221163658","doi":"https://doi.org/10.1109/lsp.2023.3244511","title":"Supervised Learning of Analysis-Sparsity Priors With Automatic Differentiation","display_name":"Supervised Learning of Analysis-Sparsity Priors With Automatic Differentiation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4221163658","doi":"https://doi.org/10.1109/lsp.2023.3244511"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3244511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3244511","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2112.07990","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039656451","display_name":"Hashem Ghanem","orcid":"https://orcid.org/0000-0003-1690-1316"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I177064439","display_name":"Universit\u00e9 de Bourgogne","ror":"https://ror.org/03k1bsr36","country_code":"FR","type":"education","lineage":["https://openalex.org/I177064439"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Hashem Ghanem","raw_affiliation_strings":["CNRS, IMB, University de Bourgogne, Nice, France"],"raw_orcid":"https://orcid.org/0000-0003-1690-1316","affiliations":[{"raw_affiliation_string":"CNRS, IMB, University de Bourgogne, Nice, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I177064439"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033768552","display_name":"Joseph Salmon","orcid":"https://orcid.org/0000-0002-3181-0634"},"institutions":[{"id":"https://openalex.org/I19894307","display_name":"Universit\u00e9 de Montpellier","ror":"https://ror.org/051escj72","country_code":"FR","type":"education","lineage":["https://openalex.org/I19894307"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Joseph Salmon","raw_affiliation_strings":["University of Montpellier, Montpellier, France"],"raw_orcid":"https://orcid.org/0000-0002-3181-0634","affiliations":[{"raw_affiliation_string":"University of Montpellier, Montpellier, France","institution_ids":["https://openalex.org/I19894307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003197490","display_name":"Nicolas Keriven","orcid":"https://orcid.org/0000-0002-3846-8763"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Keriven","raw_affiliation_strings":["CNRS, GIPSA-lab, Saint Martin d'Heres Cedex, France"],"raw_orcid":"https://orcid.org/0000-0002-3846-8763","affiliations":[{"raw_affiliation_string":"CNRS, GIPSA-lab, Saint Martin d'Heres Cedex, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210124956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065881667","display_name":"Samuel Vaiter","orcid":"https://orcid.org/0000-0002-4077-708X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Samuel Vaiter","raw_affiliation_strings":["CNRS, LJAD, University C&#x00F4;te d&#x0027;Azur, Nice, France"],"raw_orcid":"https://orcid.org/0000-0002-4077-708X","affiliations":[{"raw_affiliation_string":"CNRS, LJAD, University C&#x00F4;te d&#x0027;Azur, Nice, France","institution_ids":["https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00356133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"339","last_page":"343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9995999932289124,"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/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.9993000030517578,"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/T10271","display_name":"Seismic Imaging and Inversion Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1908","display_name":"Geophysics"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6832960844039917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5347231030464172},{"id":"https://openalex.org/keywords/dictionary-learning","display_name":"Dictionary learning","score":0.5097772479057312},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4819333553314209},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4750613868236542},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4420163929462433},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.434164434671402},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4319442808628082},{"id":"https://openalex.org/keywords/piecewise","display_name":"Piecewise","score":0.42557308077812195},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41331157088279724},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37334510684013367},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.3602010905742645},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.11551845073699951},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.10115641355514526}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6832960844039917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5347231030464172},{"id":"https://openalex.org/C2988886741","wikidata":"https://www.wikidata.org/wiki/Q25304494","display_name":"Dictionary learning","level":3,"score":0.5097772479057312},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4819333553314209},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4750613868236542},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4420163929462433},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.434164434671402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4319442808628082},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.42557308077812195},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41331157088279724},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37334510684013367},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.3602010905742645},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.11551845073699951},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.10115641355514526},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/lsp.2023.3244511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3244511","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2112.07990","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.07990","pdf_url":"https://arxiv.org/pdf/2112.07990","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,"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":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-03518852v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03518852","pdf_url":"https://hal.science/hal-03518852v1/file/learntv.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://ieeexplore.ieee.org/document/10049232","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2112.07990","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.07990","pdf_url":"https://arxiv.org/pdf/2112.07990","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,"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":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4400367867","display_name":"Variational Methods for Graph Signals","funder_award_id":"ANR-18-CE40-0005","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G7495137498","display_name":"Random Graphs in Machine Learning","funder_award_id":"ANR-21-CE23-0006","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W32371573","https://openalex.org/W1555213329","https://openalex.org/W1577338488","https://openalex.org/W1992276332","https://openalex.org/W2067706439","https://openalex.org/W2083381683","https://openalex.org/W2090457307","https://openalex.org/W2100556411","https://openalex.org/W2107844156","https://openalex.org/W2130248603","https://openalex.org/W2146738562","https://openalex.org/W2491337109","https://openalex.org/W2523352299","https://openalex.org/W2734839255","https://openalex.org/W2962727772","https://openalex.org/W3035033500","https://openalex.org/W3035674199","https://openalex.org/W3037871765","https://openalex.org/W3167249630","https://openalex.org/W3206211787","https://openalex.org/W3214861648","https://openalex.org/W4253214256","https://openalex.org/W6638908295","https://openalex.org/W6683861507","https://openalex.org/W6779923648","https://openalex.org/W6780014436"],"related_works":["https://openalex.org/W2115886818","https://openalex.org/W2466106906","https://openalex.org/W2069187387","https://openalex.org/W2509955295","https://openalex.org/W2572092625","https://openalex.org/W1987225540","https://openalex.org/W2363993830","https://openalex.org/W2561456314","https://openalex.org/W2249096836","https://openalex.org/W1992008660"],"abstract_inverted_index":{"Sparsity":[0],"priors":[1],"are":[2],"commonly":[3],"used":[4],"in":[5],"denoising":[6],"and":[7,33,43,71,175],"image":[8],"reconstruction.":[9],"For":[10,154],"analysis-type":[11],"priors,":[12],"a":[13,16,52,61,110],"dictionary":[14,30,78,149],"defines":[15,51],"representation":[17],"of":[18,40,104,122,167],"signals":[19,42],"that":[20,139],"is":[21,31,34,67],"likely":[22],"to":[23,35,109,118,161,165],"be":[24,36,58,86],"sparse.":[25],"In":[26,95],"most":[27],"situations,":[28],"this":[29,65,96,123],"unknown,":[32],"recovered":[37],"from":[38,150],"pairs":[39],"ground-truth":[41],"measurements,":[44],"by":[45,101],"minimizing":[46],"the":[47,77,90,102,105,120,128,144,155],"reconstruction":[48],"error.":[49],"This":[50],"hierarchical":[53],"optimization":[54],"problem,":[55],"which":[56,130,170],"can":[57,85],"cast":[59],"as":[60,69],"bi-level":[62],"optimization.":[63],"Yet,":[64],"problem":[66],"unsolvable,":[68],"reconstructions":[70,84,100],"their":[72],"derivative":[73],"<italic":[74,125],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[75,126],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">w.r.t.</i>":[76,127],"have":[79],"no":[80],"closed-form":[81],"expression.":[82],"However,":[83],"iteratively":[87],"computed":[88],"using":[89],"Forward-Backward":[91],"splitting":[92],"(FB)":[93],"algorithm.":[94],"letter,":[97],"we":[98,114,131,159],"approximate":[99],"output":[103,124],"FB":[106],"algorithm,":[107],"up":[108],"linear":[111],"transformation.":[112],"Then,":[113],"leverage":[115],"automatic":[116],"differentiation":[117],"evaluate":[119],"gradient":[121,135],"dictionary,":[129],"learn":[132],"with":[133],"projected":[134],"descent.":[136],"Experiments":[137],"show":[138],"our":[140,163],"algorithm":[141],"successfully":[142],"learns":[143],"1D":[145],"Total":[146],"Variation":[147],"(TV)":[148],"piecewise":[151],"constant":[152],"signals.":[153],"same":[156],"case":[157],"study,":[158],"propose":[160],"constrain":[162],"search":[164],"dictionaries":[166],"0-centered":[168],"columns,":[169],"removes":[171],"undesired":[172],"local":[173],"minima":[174],"improves":[176],"numerical":[177],"stability.":[178]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}