{"id":"https://openalex.org/W7161589084","doi":"https://doi.org/10.48550/arxiv.2605.15240","title":"On Kernel Eigen-alignments of KRR: Reconstruction and Generalization","display_name":"On Kernel Eigen-alignments of KRR: Reconstruction and Generalization","publication_year":2026,"publication_date":"2026-05-14","ids":{"openalex":"https://openalex.org/W7161589084","doi":"https://doi.org/10.48550/arxiv.2605.15240"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.15240","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15240","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.15240","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136436469","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0002-9647-6913"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136447463","display_name":"Ernest Fokoue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fokoue, Ernest","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136453953","display_name":"Richard Lange","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lange, Richard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133960784","display_name":"Daniel Krutz","orcid":"https://orcid.org/0000-0002-0310-3086"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krutz, Daniel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.5116999745368958,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.5116999745368958,"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/T10057","display_name":"Face and Expression Recognition","score":0.19499999284744263,"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/T10320","display_name":"Neural Networks and Applications","score":0.14470000565052032,"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/generalization","display_name":"Generalization","score":0.8349999785423279},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6751000285148621},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.6194000244140625},{"id":"https://openalex.org/keywords/generalization-error","display_name":"Generalization error","score":0.513700008392334},{"id":"https://openalex.org/keywords/kernel-embedding-of-distributions","display_name":"Kernel embedding of distributions","score":0.5065000057220459},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.491100013256073},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.48510000109672546},{"id":"https://openalex.org/keywords/variable-kernel-density-estimation","display_name":"Variable kernel density estimation","score":0.4650000035762787}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8349999785423279},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6751000285148621},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6456000208854675},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.6194000244140625},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.513700008392334},{"id":"https://openalex.org/C134517425","wikidata":"https://www.wikidata.org/wiki/Q16000131","display_name":"Kernel embedding of distributions","level":4,"score":0.5065000057220459},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4699000120162964},{"id":"https://openalex.org/C195699287","wikidata":"https://www.wikidata.org/wiki/Q7915722","display_name":"Variable kernel density estimation","level":4,"score":0.4650000035762787},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46000000834465027},{"id":"https://openalex.org/C182335926","wikidata":"https://www.wikidata.org/wiki/Q17093020","display_name":"Kernel principal component analysis","level":4,"score":0.4438000023365021},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.4325999915599823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41019999980926514},{"id":"https://openalex.org/C75866337","wikidata":"https://www.wikidata.org/wiki/Q7280263","display_name":"Radial basis function kernel","level":4,"score":0.4092000126838684},{"id":"https://openalex.org/C71134354","wikidata":"https://www.wikidata.org/wiki/Q458825","display_name":"Kernel density estimation","level":3,"score":0.3901999890804291},{"id":"https://openalex.org/C160446489","wikidata":"https://www.wikidata.org/wiki/Q7226642","display_name":"Polynomial kernel","level":4,"score":0.3596000075340271},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34630000591278076},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.31679999828338623},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C2776879701","wikidata":"https://www.wikidata.org/wiki/Q25048660","display_name":"Multiple kernel learning","level":4,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.15240","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15240","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.15240","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15240","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,9,34,59,66,83,97,117,138,144,154],"critical":[4],"role":[5],"of":[6,36,40,69,100,141],"eigenalignments":[7],"between":[8,27,187],"kernel":[10,31,84,133,139],"matrix":[11,101],"and":[12,33,38,103,115],"learning":[13,20],"targets":[14],"in":[15,19,30,62,132],"achieving":[16],"robust":[17],"generalization":[18,28,94,118,168,178],"problems.":[21],"We":[22,54],"establish":[23,166],"a":[24,43,90,123,167],"direct":[25],"connection":[26],"performance":[29],"methods":[32],"estimation":[35,98,173],"eigenvectors":[37],"eigenvalues":[39,102],"matrices,":[41],"offering":[42],"more":[44],"intuitive":[45],"understanding":[46],"compared":[47],"to":[48,82],"prior":[49],"work":[50],"with":[51,106],"minimal":[52],"assumptions.":[53],"also":[55],"show":[56],"that,":[57],"since":[58],"prediction":[60],"task":[61],"KRR":[63],"is":[64,140],"essentially":[65],"weighted":[67],"sum":[68],"eigenvectors/singular":[70],"vectors,":[71],"by":[72,80],"analyzing":[73],"how":[74],"much":[75],"error":[76,95,119,147,156],"can":[77,87,148],"be":[78,149],"caused":[79],"perturbations":[81],"matrix,":[85],"we":[86,165],"then":[88],"derive":[89],"bound":[91,169],"on":[92,112,116],"this":[93],"using":[96],"stability":[99],"eigenvectors.":[104],"Compared":[105],"previous":[107],"work,":[108],"our":[109],"analysis":[110],"concentrates":[111],"finite-sample":[113],"settings":[114],"arising":[120],"from":[121,170],"having":[122],"suboptimal":[124],"finite":[125],"training":[126],"set.":[127],"Our":[128],"findings":[129],"reveal":[130],"that":[131,153,176],"methods,":[134],"as":[135,137],"long":[136],"high":[142],"rank,":[143],"near-zero":[145],"reconstruction":[146,155],"trivially":[150],"obtained,":[151],"implying":[152],"will":[157],"have":[158],"limited":[159],"predictive":[160],"power":[161],"for":[162],"generalization.":[163],"Finally,":[164],"an":[171],"eigenvalues/eigenvectors":[172],"perspective,":[174],"showing":[175],"strong":[177],"requires":[179],"increasing":[180],"eigenvector":[181],"alignment,":[182],"eigenvalue":[183],"magnitude,":[184],"or":[185],"gaps":[186],"consecutive":[188],"eigenvalues.":[189]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-19T00:00:00"}