{"id":"https://openalex.org/W7216012011","doi":"https://doi.org/10.48550/arxiv.2610.00564","title":"Attention Kernels for Learning Maps Between Heavy-Tailed Measures","display_name":"Attention Kernels for Learning Maps Between Heavy-Tailed Measures","alternate_titles":[],"publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7216012011","doi":"https://doi.org/10.48550/arxiv.2610.00564"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.00564","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00564","pdf_url":"https://arxiv.org/pdf/2610.00564","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"},"parent_works":[],"lineage":["https://openalex.org/W7216012011"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.00564","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5155491886","display_name":"Kailen Hargenrader","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hargenrader, Kailen","raw_affiliation_strings":["Computing and Mathematical Sciences California Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computing and Mathematical Sciences California Institute of Technology","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071955091","display_name":"Edoardo Calvello","orcid":"https://orcid.org/0009-0002-6722-823X","observed_orcids":["https://orcid.org/0009-0002-6722-823X"]},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]},{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Calvello, Edoardo","raw_affiliation_strings":["Lawrence Berkeley National Laboratory University of California , Berkeley ICSI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory University of California , Berkeley ICSI","institution_ids":["https://openalex.org/I1297971548","https://openalex.org/I148283060","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5156240198","display_name":"Bohan Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Bohan","raw_affiliation_strings":["Computing and Mathematical Sciences California Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computing and Mathematical Sciences California Institute of Technology","institution_ids":["https://openalex.org/I122411786"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.3174000084400177,"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/T10320","display_name":"Neural Networks and Applications","score":0.3174000084400177,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.17569999396800995,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.10559999942779541,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"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/heavy-tailed-distributions","display_name":"heavy-tailed distributions","score":0.8119999766349792},{"id":"https://openalex.org/keywords/operator-learning","display_name":"operator learning","score":0.7139999866485596},{"id":"https://openalex.org/keywords/probability-measures","display_name":"probability measures","score":0.5809999704360962},{"id":"https://openalex.org/keywords/softmax-function","display_name":"softmax","score":0.32899999618530273},{"id":"https://openalex.org/keywords/ensemble-collapse","display_name":"ensemble collapse","score":0.7639999985694885},{"id":"https://openalex.org/keywords/wasserstein-distance","display_name":"Wasserstein distance","score":0.8450000286102295},{"id":"https://openalex.org/keywords/energy-distance","display_name":"energy distance","score":0.6660000085830688},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.32100000977516174},{"id":"https://openalex.org/keywords/matrix-inverse","display_name":"matrix inverse","score":0.4519999921321869}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.7174999713897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5767999887466431},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5702999830245972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4973999857902527},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.47909998893737793},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4214000105857849},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3993000090122223},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3188000023365021},{"id":"https://openalex.org/C75235859","wikidata":"https://www.wikidata.org/wiki/Q582659","display_name":"Exponential growth","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.31450000405311584},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.30889999866485596},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.3037000000476837},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C92207270","wikidata":"https://www.wikidata.org/wiki/Q939253","display_name":"Matrix norm","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C71134354","wikidata":"https://www.wikidata.org/wiki/Q458825","display_name":"Kernel density estimation","level":3,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.00564","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00564","pdf_url":"https://arxiv.org/pdf/2610.00564","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.2610.00564","doi":"https://doi.org/10.48550/arxiv.2610.00564","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.00564","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:2610.00564","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00564","pdf_url":"https://arxiv.org/pdf/2610.00564","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":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7216012011.pdf","grobid_xml":"https://content.openalex.org/works/W7216012011.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1982534687","https://openalex.org/W2048649579","https://openalex.org/W2083252561","https://openalex.org/W2626778328","https://openalex.org/W2894384847","https://openalex.org/W2979786244","https://openalex.org/W3034573343","https://openalex.org/W3039502308","https://openalex.org/W3118310857","https://openalex.org/W4226261765","https://openalex.org/W4237850425","https://openalex.org/W4280634204","https://openalex.org/W4299457904","https://openalex.org/W4320854821","https://openalex.org/W4376123079","https://openalex.org/W4386839902","https://openalex.org/W4394698525","https://openalex.org/W4403587871","https://openalex.org/W4404307029","https://openalex.org/W4409147637","https://openalex.org/W4410431797","https://openalex.org/W4411881822","https://openalex.org/W4416999248","https://openalex.org/W7124452498","https://openalex.org/W7160868005","https://openalex.org/W7162663684","https://openalex.org/W7166176883"],"related_works":["https://openalex.org/W3212687717","https://openalex.org/W7221818835","https://openalex.org/W7092287766","https://openalex.org/W7160393803","https://openalex.org/W7125700450","https://openalex.org/W7133986771","https://openalex.org/W7220965020","https://openalex.org/W7137246530","https://openalex.org/W3091156754","https://openalex.org/W3210498880"],"abstract_inverted_index":{"Operator":[0],"learning":[1,42,143],"on":[2,43,72,90,97],"probability":[3],"measures":[4,11,44],"can":[5,20],"be":[6],"accomplished":[7],"with":[8,12,33,45],"transformers.":[9,62],"For":[10],"polynomial":[13],"tails,":[14],"the":[15,22,31,66,77,91,98,103,118],"exponential":[16,32],"weighting":[17],"in":[18,60],"softmax":[19,67,86],"make":[21],"corresponding":[23],"measure-level":[24],"attention":[25,54,133],"integrals":[26],"diverge.":[27],"This":[28],"motivates":[29],"replacing":[30],"slower-growing":[34,79,132],"functions.":[35],"We":[36,48,111],"construct":[37],"two":[38],"benchmarks":[39,51],"for":[40,140],"operator":[41],"closed-form":[46],"targets.":[47],"use":[49],"these":[50],"to":[52,87,126],"study":[53],"kernel":[55],"growth":[56],"and":[57,123],"data":[58,64],"transformation":[59],"post-norm":[61,141],"Without":[63],"transformation,":[65],"models":[68],"exhibit":[69],"ensemble":[70],"collapse":[71,89],"both":[73],"heavy-tailed":[74,145],"benchmarks,":[75],"while":[76],"three":[78],"kernels":[80,108,134],"avoid":[81,88],"collapse.":[82],"Symlog":[83],"preprocessing":[84],"allows":[85],"matrix":[92],"inverse":[93],"task":[94],"but":[95],"not":[96],"sheared":[99],"swap":[100],"task.":[101],"On":[102],"Gaussian":[104],"control,":[105],"all":[106],"four":[107],"perform":[109],"similarly.":[110],"also":[112],"examine":[113],"how":[114],"sample":[115],"size":[116],"affects":[117],"sensitivity":[119],"of":[120],"empirical":[121],"energy":[122],"Wasserstein":[124],"distances":[125],"tail":[127],"differences.":[128],"These":[129],"results":[130],"support":[131],"as":[135],"an":[136],"effective":[137],"design":[138],"choice":[139],"transformers":[142],"from":[144],"ensembles.":[146]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W7216012011","counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2026-10-03T00:00:00"}
