{"id":"https://openalex.org/W4281253824","doi":"https://doi.org/10.48550/arxiv.2205.09589","title":"Learning Energy Networks with Generalized Fenchel-Young Losses","display_name":"Learning Energy Networks with Generalized Fenchel-Young Losses","publication_year":2022,"publication_date":"2022-05-19","ids":{"openalex":"https://openalex.org/W4281253824","doi":"https://doi.org/10.48550/arxiv.2205.09589"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2205.09589","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.09589","pdf_url":"https://arxiv.org/pdf/2205.09589","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2205.09589","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049123454","display_name":"Mathieu Blondel","orcid":"https://orcid.org/0000-0002-2366-2993"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Blondel, Mathieu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112271335","display_name":"Felipe Llinares-L\u00f3pez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Llinares-L\u00f3pez, Felipe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043577372","display_name":"Robert Dadashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dadashi, Robert","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079135104","display_name":"L\u00e9onard Hussenot","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hussenot, L\u00e9onard","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110482875","display_name":"Matthieu Geist","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geist, Matthieu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5049123454"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9902999997138977,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9787999987602234,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/energy","display_name":"Energy (signal processing)","score":0.6683046817779541},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6623203754425049},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6548339128494263},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5508166551589966},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4771430194377899},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47123727202415466},{"id":"https://openalex.org/keywords/pairing","display_name":"Pairing","score":0.42365431785583496},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42212027311325073},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.34340131282806396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3431134521961212},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3039618134498596},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10894706845283508},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08198454976081848}],"concepts":[{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.6683046817779541},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6623203754425049},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6548339128494263},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5508166551589966},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4771430194377899},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47123727202415466},{"id":"https://openalex.org/C14103023","wikidata":"https://www.wikidata.org/wiki/Q11681459","display_name":"Pairing","level":3,"score":0.42365431785583496},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42212027311325073},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.34340131282806396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3431134521961212},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3039618134498596},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10894706845283508},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08198454976081848},{"id":"https://openalex.org/C54101563","wikidata":"https://www.wikidata.org/wiki/Q124131","display_name":"Superconductivity","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2205.09589","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.09589","pdf_url":"https://arxiv.org/pdf/2205.09589","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"doi:10.48550/arxiv.2205.09589","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2205.09589","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2205.09589","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.09589","pdf_url":"https://arxiv.org/pdf/2205.09589","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8999999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3015473028","https://openalex.org/W3201176751","https://openalex.org/W1993094293","https://openalex.org/W2029180842","https://openalex.org/W2024971119","https://openalex.org/W2057898405","https://openalex.org/W2953807518","https://openalex.org/W2258335979","https://openalex.org/W2890366349","https://openalex.org/W1971460732"],"abstract_inverted_index":{"Energy-based":[0],"models,":[1],"a.k.a.":[2],"energy":[3,10,36,56,89,102],"networks,":[4],"perform":[5],"inference":[6],"by":[7,14],"optimizing":[8],"an":[9],"function,":[11,37,79,90],"typically":[12,45,65],"parametrized":[13],"a":[15,48,74,87,96],"neural":[16],"network.":[17],"This":[18],"allows":[19],"one":[20],"to":[21,40],"capture":[22],"potentially":[23],"complex":[24],"relationships":[25],"between":[26],"inputs":[27],"and":[28,110,142],"outputs.":[29],"To":[30],"learn":[31],"the":[32,35,38,82,123,130],"parameters":[33],"of":[34,77,125,132],"solution":[39],"that":[41],"optimization":[42],"problem":[43],"is":[44],"fed":[46],"into":[47],"loss":[49,61,98],"function.":[50],"The":[51],"key":[52],"challenge":[53],"for":[54,100],"training":[55],"networks":[57],"lies":[58],"in":[59,129],"computing":[60],"gradients,":[62],"as":[63],"this":[64,70],"requires":[66],"argmin/argmax":[67,118],"differentiation.":[68,119],"In":[69],"paper,":[71],"building":[72],"upon":[73],"generalized":[75,93],"notion":[76],"conjugate":[78],"which":[80],"replaces":[81],"usual":[83],"bilinear":[84],"pairing":[85],"with":[86],"general":[88],"we":[91],"propose":[92],"Fenchel-Young":[94],"losses,":[95],"natural":[97],"construction":[99],"learning":[101,144],"networks.":[103],"Our":[104],"losses":[105,138],"enjoy":[106],"many":[107],"desirable":[108],"properties":[109],"their":[111,126],"gradients":[112],"can":[113],"be":[114],"computed":[115],"efficiently":[116],"without":[117],"We":[120,135],"also":[121],"prove":[122],"calibration":[124],"excess":[127],"risk":[128],"case":[131],"linear-concave":[133],"energies.":[134],"demonstrate":[136],"our":[137],"on":[139],"multilabel":[140],"classification":[141],"imitation":[143],"tasks.":[145]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}