{"id":"https://openalex.org/W7127437708","doi":"https://doi.org/10.48550/arxiv.2602.00987","title":"Scalable Random Wavelet Features: Efficient Non-Stationary Kernel Approximation with Convergence Guarantees","display_name":"Scalable Random Wavelet Features: Efficient Non-Stationary Kernel Approximation with Convergence Guarantees","publication_year":2026,"publication_date":"2026-02-01","ids":{"openalex":"https://openalex.org/W7127437708","doi":"https://doi.org/10.48550/arxiv.2602.00987"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.00987","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104274124","display_name":"Sawan Kumar","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kumar, Sawan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124943347","display_name":"Souvik Chakraborty","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chakraborty, Souvik","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5104274124"],"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.8083999752998352,"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":0.8083999752998352,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.07999999821186066,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.010900000110268593,"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/scalability","display_name":"Scalability","score":0.6425999999046326},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.576200008392334},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.5364999771118164},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5002999901771545},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.46129998564720154},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4462999999523163},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4092000126838684},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.40380001068115234}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6425999999046326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5796999931335449},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.576200008392334},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.5364999771118164},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5040000081062317},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5002999901771545},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4462999999523163},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.40380001068115234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3937000036239624},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3846000134944916},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.37450000643730164},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37310001254081726},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3109999895095825},{"id":"https://openalex.org/C130402806","wikidata":"https://www.wikidata.org/wiki/Q5361768","display_name":"Random field","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.30390000343322754},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C105125183","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Statistical signal processing","level":4,"score":0.2858000099658966},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2727000117301941},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C121927907","wikidata":"https://www.wikidata.org/wiki/Q1952516","display_name":"Multiresolution analysis","level":5,"score":0.26440000534057617}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.00987","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},{"id":"doi:10.48550/arxiv.2602.00987","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.00987","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.00987","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"sustainable_development_goals":[{"score":0.42230069637298584,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modeling":[0],"non-stationary":[1,69,109,166],"processes,":[2],"where":[3],"statistical":[4],"properties":[5],"vary":[6],"across":[7],"the":[8,79,108],"input":[9],"domain,":[10],"is":[11],"a":[12,24,31,64,101,114,130,146,161],"critical":[13],"challenge":[14],"in":[15],"machine":[16],"learning;":[17],"yet":[18],"most":[19],"scalable":[20,45,155],"methods":[21,48,159],"rely":[22],"on":[23,129],"simplifying":[25],"assumption":[26],"of":[27,85,132,164],"stationarity.":[28],"This":[29],"forces":[30],"difficult":[32],"trade-off:":[33],"use":[34],"expressive":[35,157],"but":[36,46],"computationally":[37],"demanding":[38],"models":[39],"like":[40,49],"Deep":[41],"Gaussian":[42],"Processes,":[43],"or":[44],"limited":[47],"Random":[50,60],"Fourier":[51],"Features":[52,62],"(RFF).":[53],"We":[54,126],"close":[55],"this":[56],"gap":[57],"by":[58,72],"introducing":[59],"Wavelet":[61],"(RWF),":[63],"framework":[65,99],"that":[66,93,138],"constructs":[67],"scalable,":[68],"kernel":[70,158],"approximations":[71],"sampling":[73],"from":[74],"wavelet":[75],"families.":[76],"By":[77],"harnessing":[78],"inherent":[80],"localization":[81],"and":[82,111,122,135,144,156],"multi-resolution":[83],"structure":[84],"wavelets,":[86],"RWF":[87,139],"generates":[88],"an":[89],"explicit":[90],"feature":[91],"map":[92],"captures":[94],"complex,":[95],"input-dependent":[96],"patterns.":[97],"Our":[98],"provides":[100],"principled":[102],"way":[103],"to":[104,107],"generalize":[105],"RFF":[106],"setting":[110],"comes":[112],"with":[113],"comprehensive":[115],"theoretical":[116],"analysis,":[117],"including":[118],"positive":[119],"definiteness,":[120],"unbiasedness,":[121],"uniform":[123],"convergence":[124],"guarantees.":[125],"demonstrate":[127],"empirically":[128],"range":[131],"challenging":[133],"synthetic":[134],"real-world":[136,165],"datasets":[137],"outperforms":[140],"stationary":[141],"random":[142],"features":[143],"offers":[145],"compelling":[147],"accuracy-efficiency":[148],"trade-off":[149],"against":[150],"more":[151],"complex":[152],"models,":[153],"unlocking":[154],"for":[160],"broad":[162],"class":[163],"problems.":[167]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-04T00:00:00"}