{"id":"https://openalex.org/W4415097570","doi":"https://doi.org/10.1088/2632-2153/ae8fb7","title":"Fisher information, training and bias in Fourier regression models","display_name":"Fisher information, training and bias in Fourier regression models","publication_year":2026,"publication_date":"2026-07-23","ids":{"openalex":"https://openalex.org/W4415097570","doi":"https://doi.org/10.1088/2632-2153/ae8fb7"},"language":"en","primary_location":{"id":"doi:10.1088/2632-2153/ae8fb7","doi":"https://doi.org/10.1088/2632-2153/ae8fb7","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ae8fb7","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1088/2632-2153/ae8fb7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080337581","display_name":"Lorenzo Pastori","orcid":"https://orcid.org/0000-0001-5882-8482","observed_orcids":["https://orcid.org/0000-0001-5882-8482"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lorenzo Pastori","raw_affiliation_strings":["Institut f\u00fcr Physik der Atmosph\u00e4re"],"raw_orcid":"https://orcid.org/0000-0001-5882-8482","affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Physik der Atmosph\u00e4re","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034118743","display_name":"Veronika Eyring","orcid":"https://orcid.org/0000-0002-6887-4885","observed_orcids":["https://orcid.org/0000-0002-6887-4885"]},"institutions":[{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Veronika Eyring","raw_affiliation_strings":["Institut f\u00fcr Physik der Atmosph\u00e4re","University of Bremen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Physik der Atmosph\u00e4re","institution_ids":[]},{"raw_affiliation_string":"University of Bremen","institution_ids":["https://openalex.org/I180437899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067513652","display_name":"Mierk Schwabe","orcid":"https://orcid.org/0000-0001-6565-5890","observed_orcids":["https://orcid.org/0000-0001-6565-5890"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mierk Schwabe","raw_affiliation_strings":["Institut f\u00fcr Physik der Atmosph\u00e4re"],"raw_orcid":"https://orcid.org/0000-0001-6565-5890","affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Physik der Atmosph\u00e4re","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3000,"currency":"USD","value_usd":3000},"apc_paid":{"value":3000,"currency":"USD","value_usd":3000},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01295465,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"4","first_page":"045048","last_page":"045048"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9965999722480774,"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"}},"topics":[{"id":"https://openalex.org/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9965999722480774,"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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.0007999999797903001,"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"}},{"id":"https://openalex.org/T11804","display_name":"Quantum many-body systems","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/fisher-information-matrix","display_name":"Fisher information matrix","score":0.9679999947547913},{"id":"https://openalex.org/keywords/quantum-neural-networks","display_name":"quantum neural networks","score":0.8769999742507935},{"id":"https://openalex.org/keywords/effective-dimension","display_name":"effective dimension","score":0.8539999723434448},{"id":"https://openalex.org/keywords/model-bias","display_name":"model bias","score":0.9269999861717224},{"id":"https://openalex.org/keywords/trainability","display_name":"trainability","score":0.8320000171661377},{"id":"https://openalex.org/keywords/quantum-machine-learning","display_name":"quantum machine learning","score":0.8199999928474426},{"id":"https://openalex.org/keywords/tensor-networks","display_name":"tensor networks","score":0.7609999775886536}],"concepts":[{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.6327000260353088},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5338000059127808},{"id":"https://openalex.org/C29406490","wikidata":"https://www.wikidata.org/wiki/Q1420659","display_name":"Fisher information","level":2,"score":0.5263000130653381},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5044999718666077},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.47780001163482666},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.45980000495910645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.445499986410141},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.44510000944137573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4372999966144562},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43290001153945923},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3833000063896179},{"id":"https://openalex.org/C115311070","wikidata":"https://www.wikidata.org/wiki/Q5347255","display_name":"Effective dimension","level":3,"score":0.367000013589859},{"id":"https://openalex.org/C103275481","wikidata":"https://www.wikidata.org/wiki/Q6787889","display_name":"Matrix representation","level":3,"score":0.35659998655319214},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.31940001249313354},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C140101238","wikidata":"https://www.wikidata.org/wiki/Q1404885","display_name":"Window function","level":3,"score":0.289900004863739},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2619999945163727},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1088/2632-2153/ae8fb7","doi":"https://doi.org/10.1088/2632-2153/ae8fb7","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ae8fb7","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2510.06945","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.06945","pdf_url":"https://arxiv.org/pdf/2510.06945","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:elib.dlr.de:226379","doi":null,"is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ae8fb7>.","pdf_url":"https://elib.dlr.de/226379/1/Pastori_2026_Mach._Learn.__Sci._Technol._7_045048.pdf","source":{"id":"https://openalex.org/S4377196266","display_name":"elib (German Aerospace Center)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2898391981","host_organization_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","host_organization_lineage":["https://openalex.org/I2898391981"],"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":"Zeitschriftenbeitrag"},{"id":"doi:10.48550/arxiv.2510.06945","doi":"https://doi.org/10.48550/arxiv.2510.06945","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.06945","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1088/2632-2153/ae8fb7","doi":"https://doi.org/10.1088/2632-2153/ae8fb7","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ae8fb7","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2411810777","display_name":null,"funder_award_id":"bd1179","funder_id":"https://openalex.org/F4320318393","funder_display_name":"Deutsches Klimarechenzentrum"},{"id":"https://openalex.org/G8396100740","display_name":null,"funder_award_id":"EY 22/2-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4303701741","display_name":"Bundesministerium f\u00fcr Wirtschaft und Klimaschutz","ror":"https://ror.org/02vgg2808"},{"id":"https://openalex.org/F4320318393","display_name":"Deutsches Klimarechenzentrum","ror":"https://ror.org/03ztgj037"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320322379","display_name":"Gottfried Wilhelm Leibniz Universit\u00e4t Hannover","ror":"https://ror.org/0304hq317"},{"id":"https://openalex.org/F4320334763","display_name":"Leibniz-Gemeinschaft","ror":"https://ror.org/01n6r0e97"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Motivated":[1],"by":[2],"the":[3,25,41,54,57,62,75,93,110,119,142,149,179,192,205,218],"growing":[4],"interest":[5,190],"in":[6,10,103],"quantum":[7,12],"machine":[8,220],"learning,":[9],"particular":[11],"neural":[13],"networks":[14],"(QNNs),":[15],"we":[16,136],"study":[17,53],"how":[18,72],"recently":[19],"introduced":[20],"evaluation":[21],"metrics":[22],"based":[23],"on":[24],"Fisher":[26],"information":[27],"matrix":[28],"(FIM)":[29],"are":[30,116,215],"effective":[31,58],"for":[32,83,113,144,191,217],"predicting":[33],"their":[34,169],"training":[35,77],"and":[36,49,52,61,78,107,147,164,166,212],"prediction":[37],"performance.":[38,79,108],"We":[39,80,171],"exploit":[40],"equivalence":[42],"between":[43,56,207],"a":[44,65,68,84,98,104,124,152,174,186],"broad":[45],"class":[46],"of":[47,64,141,178,188,194,204],"QNNs":[48],"Fourier":[50,145,181],"models,":[51,182],"interplay":[55,206],"dimension":[59],"(ED)":[60],"bias":[63],"model":[66,85],"towards":[67,92,118],"given":[69],"task,":[70],"investigating":[71],"these":[73,134,198],"affect":[74],"model\u2019s":[76,153],"show":[81],"that":[82,86,115],"is":[87,127],"completely":[88],"agnostic,":[89],"or":[90],"unbiased,":[91],"function":[94,120],"to":[95,121,158,167],"be":[96,122,185],"learned,":[97],"higher":[99],"ED":[100,126,163],"likely":[101,128],"results":[102],"better":[105],"trainability":[106],"On":[109],"other":[111],"hand,":[112],"models":[114,146,160],"biased":[117],"learned":[123],"lower":[125],"beneficial":[129],"during":[130],"training.":[131,170],"To":[132],"obtain":[133],"results,":[135],"derive":[137],"an":[138,201],"analytical":[139],"expression":[140],"FIM":[143],"identify":[148],"features":[150],"controlling":[151],"ED.":[154],"This":[155],"allows":[156],"us":[157],"construct":[159],"with":[161],"tunable":[162],"bias,":[165],"compare":[168],"furthermore":[172],"introduce":[173],"tensor":[175],"network":[176],"representation":[177],"considered":[180],"which":[183,214],"could":[184],"tool":[187],"independent":[189],"analysis":[193],"QNN":[195],"models.":[196],"Overall,":[197],"findings":[199],"provide":[200],"explicit":[202],"example":[203],"geometrical":[208],"properties,":[209],"model-task":[210],"alignment":[211],"training,":[213],"relevant":[216],"broader":[219],"learning":[221],"community.":[222]},"counts_by_year":[],"updated_date":"2026-10-15T10:00:46.086208","created_date":"2025-10-13T00:00:00"}