{"id":"https://openalex.org/W4399837741","doi":"https://doi.org/10.48550/arxiv.2406.12678","title":"Contraction rates for conjugate gradient and Lanczos approximate posteriors in Gaussian process regression","display_name":"Contraction rates for conjugate gradient and Lanczos approximate posteriors in Gaussian process regression","publication_year":2024,"publication_date":"2024-06-18","ids":{"openalex":"https://openalex.org/W4399837741","doi":"https://doi.org/10.48550/arxiv.2406.12678"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.12678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.12678","pdf_url":"https://arxiv.org/pdf/2406.12678","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":"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/2406.12678","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025913656","display_name":"Bernhard Stankewitz","orcid":"https://orcid.org/0000-0002-3135-8174"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Stankewitz, Bernhard","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087567946","display_name":"Botond Szab\u00f3","orcid":"https://orcid.org/0000-0002-5526-8747"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Szabo, Botond","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025913656"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.986299991607666,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.986299991607666,"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/T11324","display_name":"Spectroscopy Techniques in Biomedical and Chemical Research","score":0.9266999959945679,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lanczos-resampling","display_name":"Lanczos resampling","score":0.7662372589111328},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.6770938038825989},{"id":"https://openalex.org/keywords/contraction","display_name":"Contraction (grammar)","score":0.6272187829017639},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.6103278398513794},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.49697592854499817},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4464013874530792},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3990434408187866},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3223930597305298},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.2911473512649536},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.11022603511810303},{"id":"https://openalex.org/keywords/internal-medicine","display_name":"Internal medicine","score":0.0821724534034729}],"concepts":[{"id":"https://openalex.org/C119256216","wikidata":"https://www.wikidata.org/wiki/Q913012","display_name":"Lanczos resampling","level":3,"score":0.7662372589111328},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.6770938038825989},{"id":"https://openalex.org/C163415756","wikidata":"https://www.wikidata.org/wiki/Q126473","display_name":"Contraction (grammar)","level":2,"score":0.6272187829017639},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.6103278398513794},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.49697592854499817},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4464013874530792},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3990434408187866},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3223930597305298},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2911473512649536},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.11022603511810303},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0821724534034729},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.12678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.12678","pdf_url":"https://arxiv.org/pdf/2406.12678","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.12678","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.12678","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:2406.12678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.12678","pdf_url":"https://arxiv.org/pdf/2406.12678","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399837741.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2357291060","https://openalex.org/W1484683478","https://openalex.org/W4239321356","https://openalex.org/W2743382746","https://openalex.org/W2377578636","https://openalex.org/W1601294834","https://openalex.org/W2031196824","https://openalex.org/W2081465995","https://openalex.org/W1964286703","https://openalex.org/W2169866437"],"abstract_inverted_index":{"Due":[0],"to":[1,53,161,189],"their":[2],"flexibility":[3],"and":[4,20,74],"theoretical":[5,98,195],"tractability":[6],"Gaussian":[7],"process":[8],"(GP)":[9],"regression":[10],"models":[11,29],"have":[12,95],"become":[13],"a":[14,105,133],"central":[15],"topic":[16],"in":[17,27,67,91,122,145],"modern":[18,68,166],"statistics":[19],"machine":[21],"learning.":[22],"While":[23],"the":[24,37,40,76,83,113,129,138,162,173,180],"true":[25],"posterior":[26,139],"these":[28],"is":[30,71],"given":[31,66],"explicitly,":[32],"numerical":[33,174,200],"evaluations":[34],"depend":[35],"on":[36,156],"inversion":[38],"of":[39,78,82,107,115,124,128,137,165,179,186],"augmented":[41],"kernel":[42,130,187],"matrix":[43,131,157],"$":[44,54,56],"K":[45],"+":[46],"\u03c3^2":[47],"I":[48],"$,":[49],"which":[50,63,141],"requires":[51],"up":[52],"O(n^3)":[55],"operations.":[57],"For":[58],"large":[59,147],"sample":[60],"sizes":[61],"n,":[62],"are":[64,88,142,152,197],"typically":[65,94],"applications,":[69,149],"this":[70,101],"computationally":[72],"infeasible":[73],"necessitates":[75],"use":[77],"an":[79],"approximate":[80,126],"version":[81],"posterior.":[84],"Although":[85],"such":[86],"methods":[87],"widely":[89],"used":[90],"practice,":[92],"they":[93,151],"very":[96],"limtied":[97],"underpinning.":[99],"In":[100],"context,":[102],"we":[103],"analyze":[104],"class":[106],"recently":[108],"proposed":[109],"approximation":[110,136],"algorithms":[111],"from":[112,172],"field":[114],"Probabilistic":[116],"numerics.":[117],"They":[118],"can":[119],"be":[120],"interpreted":[121],"terms":[123],"Lanczos":[125],"eigenvectors":[127],"or":[132],"conjugate":[134],"gradient":[135],"mean,":[140],"particularly":[143],"advantageous":[144],"truly":[146],"scale":[148],"as":[150],"fundamentally":[153],"only":[154],"based":[155],"vector":[158],"multiplications":[159],"amenable":[160],"GPU":[163],"acceleration":[164],"software":[167],"frameworks.":[168],"We":[169],"combine":[170],"result":[171],"analysis":[175],"literature":[176],"with":[177],"state":[178],"art":[181],"concentration":[182],"results":[183],"for":[184],"spectra":[185],"matrices":[188],"obtain":[190],"minimax":[191],"contraction":[192],"rates.":[193],"Our":[194],"findings":[196],"illustrated":[198],"by":[199],"experiments.":[201]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2024-06-20T00:00:00"}