{"id":"https://openalex.org/W4303449264","doi":"https://doi.org/10.48550/arxiv.2210.01883","title":"Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions","display_name":"Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions","publication_year":2022,"publication_date":"2022-10-04","ids":{"openalex":"https://openalex.org/W4303449264","doi":"https://doi.org/10.48550/arxiv.2210.01883"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2210.01883","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.01883","pdf_url":"https://arxiv.org/pdf/2210.01883","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":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.01883","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023858028","display_name":"Daniel D. Johnson","orcid":"https://orcid.org/0000-0003-3119-5560"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Johnson, Daniel D.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079366629","display_name":"Ayoub El Hanchi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanchi, Ayoub El","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054711904","display_name":"Chris J. Maddison","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maddison, Chris J.","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023858028"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9348999857902527,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9146000146865845,"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/kernel","display_name":"Kernel (algebra)","score":0.6813051104545593},{"id":"https://openalex.org/keywords/eigenfunction","display_name":"Eigenfunction","score":0.5758672952651978},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.570513129234314},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5441409945487976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5118018984794617},{"id":"https://openalex.org/keywords/kernel-embedding-of-distributions","display_name":"Kernel embedding of distributions","score":0.4979879856109619},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.45682835578918457},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.44954460859298706},{"id":"https://openalex.org/keywords/kernel-principal-component-analysis","display_name":"Kernel principal component analysis","score":0.44878438115119934},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4180281162261963},{"id":"https://openalex.org/keywords/multiple-kernel-learning","display_name":"Multiple kernel learning","score":0.4175080358982086},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.36120015382766724},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3428959250450134},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.270962655544281},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.22776395082473755},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.19209834933280945},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.08484289050102234}],"concepts":[{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6813051104545593},{"id":"https://openalex.org/C128803854","wikidata":"https://www.wikidata.org/wiki/Q1307821","display_name":"Eigenfunction","level":3,"score":0.5758672952651978},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.570513129234314},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5441409945487976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5118018984794617},{"id":"https://openalex.org/C134517425","wikidata":"https://www.wikidata.org/wiki/Q16000131","display_name":"Kernel embedding of distributions","level":4,"score":0.4979879856109619},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.45682835578918457},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.44954460859298706},{"id":"https://openalex.org/C182335926","wikidata":"https://www.wikidata.org/wiki/Q17093020","display_name":"Kernel principal component analysis","level":4,"score":0.44878438115119934},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4180281162261963},{"id":"https://openalex.org/C2776879701","wikidata":"https://www.wikidata.org/wiki/Q25048660","display_name":"Multiple kernel learning","level":4,"score":0.4175080358982086},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.36120015382766724},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3428959250450134},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.270962655544281},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.22776395082473755},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.19209834933280945},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.08484289050102234},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2210.01883","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.01883","pdf_url":"https://arxiv.org/pdf/2210.01883","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2210.01883","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.01883","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.01883","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.01883","pdf_url":"https://arxiv.org/pdf/2210.01883","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1984421104","https://openalex.org/W2393746448","https://openalex.org/W2512565647","https://openalex.org/W2127229869","https://openalex.org/W2001772920","https://openalex.org/W2905418897","https://openalex.org/W2027376491","https://openalex.org/W2398887903","https://openalex.org/W2149803014","https://openalex.org/W2071590642"],"abstract_inverted_index":{"Contrastive":[0],"learning":[1,7,23,29,133],"is":[2,73],"a":[3,34,42,62,76,88,93,122],"powerful":[4],"framework":[5],"for":[6,109],"self-supervised":[8],"representations":[9],"that":[10,19,32,41,65,127],"generalize":[11],"well":[12,152],"to":[13,131],"downstream":[14,110],"supervised":[15],"tasks.":[16],"We":[17,38,105],"show":[18,119],"multiple":[20],"existing":[21],"contrastive":[22,132],"methods":[24],"can":[25,135],"be":[26],"reinterpreted":[27],"as":[28,151,153],"kernel":[30,49,149],"functions":[31],"approximate":[33],"fixed":[35],"positive-pair":[36,89],"kernel.":[37],"then":[39],"prove":[40],"simple":[43],"representation":[44],"obtained":[45],"by":[46],"combining":[47],"this":[48],"with":[50],"PCA":[51,116,130],"provably":[52],"minimizes":[53],"the":[54,79,85,100,139,144,148,155],"worst-case":[55],"approximation":[56],"error":[57],"of":[58,78,84,87,102,124],"linear":[59,111],"predictors,":[60],"under":[61],"straightforward":[63],"assumption":[64],"positive":[66],"pairs":[67],"have":[68],"similar":[69],"labels.":[70],"Our":[71],"analysis":[72],"based":[74],"on":[75,121,147,154],"decomposition":[77],"target":[80],"function":[81],"in":[82],"terms":[83],"eigenfunctions":[86,98],"Markov":[90,140],"chain,":[91],"and":[92,99,118],"surprising":[94],"equivalence":[95],"between":[96],"these":[97],"output":[101],"Kernel":[103,115,129],"PCA.":[104],"give":[106],"generalization":[107],"bounds":[108],"prediction":[112],"using":[113],"our":[114],"representation,":[117],"empirically":[120],"set":[123],"synthetic":[125],"tasks":[126],"applying":[128],"models":[134],"indeed":[136],"approximately":[137],"recover":[138],"chain":[141],"eigenfunctions,":[142],"although":[143],"accuracy":[145],"depends":[146],"parameterization":[150],"augmentation":[156],"strength.":[157]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}