{"id":"https://openalex.org/W4402701477","doi":"https://doi.org/10.48550/arxiv.2408.13591","title":"Optimal Kernel Quantile Learning with Random Features","display_name":"Optimal Kernel Quantile Learning with Random Features","alternate_titles":[],"publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4402701477","doi":"https://doi.org/10.48550/arxiv.2408.13591"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2408.13591","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.13591","pdf_url":"https://arxiv.org/pdf/2408.13591","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"},"parent_works":[],"lineage":["https://openalex.org/W4402701477"],"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/2408.13591","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000776948","display_name":"Caixing Wang","orcid":"https://orcid.org/0009-0009-3068-6094","observed_orcids":["https://orcid.org/0009-0009-3068-6094"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Caixing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101698092","display_name":"Xingdong Feng","orcid":"https://orcid.org/0000-0002-6091-8169","observed_orcids":["https://orcid.org/0000-0002-6091-8169"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Xingdong","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":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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9330999851226807,"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":0.9330999851226807,"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/T12676","display_name":"Machine Learning and ELM","score":0.031599998474121094,"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":0.01489999983459711,"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/random-features","display_name":"random features","score":0.9589999914169312},{"id":"https://openalex.org/keywords/kernel-ridge-regression","display_name":"kernel ridge regression","score":0.8270000219345093},{"id":"https://openalex.org/keywords/learning-rate","display_name":"learning rate","score":0.6570000052452087},{"id":"https://openalex.org/keywords/minimax-optimality","display_name":"minimax optimality","score":0.8529999852180481},{"id":"https://openalex.org/keywords/heavy-tailed-noise","display_name":"heavy-tailed noise","score":0.8270000219345093},{"id":"https://openalex.org/keywords/data-heterogeneity","display_name":"data heterogeneity","score":0.6129999756813049}],"concepts":[{"id":"https://openalex.org/C118671147","wikidata":"https://www.wikidata.org/wiki/Q578714","display_name":"Quantile","level":2,"score":0.69197016954422},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6629788875579834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5051878094673157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46943309903144836},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38697972893714905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36362284421920776},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.333374559879303},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.10489186644554138}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2408.13591","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.13591","pdf_url":"https://arxiv.org/pdf/2408.13591","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":"doi:10.48550/arxiv.2408.13591","doi":"https://doi.org/10.48550/arxiv.2408.13591","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2408.13591","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.13591","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.13591","pdf_url":"https://arxiv.org/pdf/2408.13591","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7288932155","display_name":null,"funder_award_id":"12371270","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402701477.pdf","grobid_xml":"https://content.openalex.org/works/W4402701477.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1560724230","https://openalex.org/W1970781863","https://openalex.org/W1992641732","https://openalex.org/W2012501405","https://openalex.org/W2070272652","https://openalex.org/W2092622249","https://openalex.org/W2096904991","https://openalex.org/W2123395972","https://openalex.org/W2144902422","https://openalex.org/W2169025130","https://openalex.org/W2171155677","https://openalex.org/W2185932763","https://openalex.org/W2415274228","https://openalex.org/W2566079294","https://openalex.org/W2568875900","https://openalex.org/W2726134516","https://openalex.org/W2884243924","https://openalex.org/W2891234027","https://openalex.org/W2911867426","https://openalex.org/W2962939986","https://openalex.org/W2963013450","https://openalex.org/W2963020641","https://openalex.org/W2963173208","https://openalex.org/W2963518130","https://openalex.org/W2963705340","https://openalex.org/W3034116706","https://openalex.org/W3038640622","https://openalex.org/W3109802576","https://openalex.org/W3125188740","https://openalex.org/W3132304818","https://openalex.org/W3141455185","https://openalex.org/W3157752112","https://openalex.org/W3167838442","https://openalex.org/W3178814403","https://openalex.org/W3183420805","https://openalex.org/W3199180939","https://openalex.org/W4214928205","https://openalex.org/W4256521831","https://openalex.org/W4292363360","https://openalex.org/W4298876635","https://openalex.org/W4385768223","https://openalex.org/W4388125274","https://openalex.org/W4391131955","https://openalex.org/W7043766663","https://openalex.org/W7133190237","https://openalex.org/W7133205309","https://openalex.org/W7219275878"],"related_works":["https://openalex.org/W7221823478","https://openalex.org/W4388125274","https://openalex.org/W2920921098","https://openalex.org/W3170454393","https://openalex.org/W7133338386","https://openalex.org/W2171155677","https://openalex.org/W2549898883","https://openalex.org/W6910734794","https://openalex.org/W2885554660"],"abstract_inverted_index":{"The":[0],"random":[1,26,50],"feature":[2],"(RF)":[3],"approach":[4],"is":[5],"a":[6,42,66,72,110,171],"well-established":[7],"and":[8,70,77,170],"efficient":[9],"tool":[10],"for":[11,55,86],"scalable":[12],"kernel":[13,22,46,134],"methods,":[14],"but":[15],"existing":[16],"literature":[17],"has":[18,30],"primarily":[19],"focused":[20],"on":[21,91],"ridge":[23],"regression":[24,48],"with":[25,36,49,131,151],"features":[27,51],"(KRR-RF),":[28],"which":[29,53,96],"limitations":[31],"in":[32,62,158],"handling":[33],"heterogeneous":[34],"data":[35,173],"heavy-tailed":[37],"noises.":[38],"This":[39],"paper":[40],"presents":[41],"generalization":[43],"study":[44,80],"of":[45,58,94],"quantile":[47,125],"(KQR-RF),":[52],"accounts":[54],"the":[56,59,82,92,119,123,132,141,159],"non-smoothness":[57],"check":[60],"loss":[61],"KQR-RF":[63,76,87],"by":[64],"introducing":[65],"refined":[67],"error":[68,143],"decomposition":[69],"establishing":[71],"novel":[73],"connection":[74],"between":[75],"KRR-RF.":[78],"Our":[79],"establishes":[81],"capacity-dependent":[83,142],"learning":[84,161],"rates":[85],"under":[88],"mild":[89],"conditions":[90],"number":[93],"RFs,":[95],"are":[97,175],"minimax":[98],"optimal":[99],"up":[100],"to":[101,117,149],"some":[102],"logarithmic":[103],"factors.":[104],"Importantly,":[105],"our":[106,139,165],"theoretical":[107,166],"results,":[108],"utilizing":[109],"data-dependent":[111],"sampling":[112],"strategy,":[113],"can":[114,145],"be":[115,147],"extended":[116],"cover":[118],"agnostic":[120],"setting":[121],"where":[122],"target":[124],"function":[126],"may":[127],"not":[128],"precisely":[129],"align":[130],"assumed":[133],"space.":[135],"By":[136],"slightly":[137],"modifying":[138],"assumptions,":[140],"analysis":[144],"also":[146],"applied":[148],"cases":[150],"Lipschitz":[152],"continuous":[153],"losses,":[154],"enabling":[155],"broader":[156],"applications":[157],"machine":[160],"community.":[162],"To":[163],"validate":[164],"findings,":[167],"simulated":[168],"experiments":[169],"real":[172],"application":[174],"conducted.":[176]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4402701477","counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2024-09-21T00:00:00"}
