{"id":"https://openalex.org/W3045204686","doi":"https://doi.org/10.3934/fods.2020014","title":"Adaptive random Fourier features with Metropolis sampling","display_name":"Adaptive random Fourier features with Metropolis sampling","alternate_titles":[],"publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3045204686","doi":"https://doi.org/10.3934/fods.2020014","mag":"3045204686"},"language":"en","primary_location":{"id":"doi:10.3934/fods.2020014","doi":"https://doi.org/10.3934/fods.2020014","is_oa":true,"landing_page_url":"https://doi.org/10.3934/fods.2020014","pdf_url":null,"source":{"id":"https://openalex.org/S4210212798","display_name":"Foundations of Data Science","issn_l":"2639-8001","issn":["2639-8001"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","jufo-1","norway-1","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310315844","host_organization_name":"American Institute of Mathematical Sciences","host_organization_lineage":["https://openalex.org/P4310315844"],"host_organization_lineage_names":["American Institute of Mathematical Sciences"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foundations of Data Science","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W3045204686"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.3934/fods.2020014","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064129060","display_name":"Aku Kammonen","orcid":"https://orcid.org/0000-0002-8458-0852","observed_orcids":["https://orcid.org/0000-0002-8458-0852"]},"institutions":[],"countries":[],"is_corresponding":true,"contributor_roles":[],"raw_author_name":"Aku Kammonen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067431568","display_name":"Jonas Kiessling","orcid":"https://orcid.org/0000-0001-6061-3456","observed_orcids":["https://orcid.org/0000-0001-6061-3456"]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Jonas Kiessling","raw_affiliation_strings":["H-Ai AB, Grevgatan 23,114 53, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"H-Ai AB, Grevgatan 23,114 53, Stockholm, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014213782","display_name":"Petr Plech\u00e1\u010d","orcid":"https://orcid.org/0000-0003-2102-4485","observed_orcids":["https://orcid.org/0000-0003-2102-4485"]},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Petr Plech\u00e1\u010d","raw_affiliation_strings":["Department of Mathematical Sciences, University of Delaware, Newark, DE 19716, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematical Sciences, University of Delaware, Newark, DE 19716, USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034216342","display_name":"Mattias Sandberg","orcid":"https://orcid.org/0000-0003-2669-359X","observed_orcids":["https://orcid.org/0000-0003-2669-359X"]},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Mattias Sandberg","raw_affiliation_strings":["Department of Mathematics, Royal Institute of Technology, 100 44, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Royal Institute of Technology, 100 44, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004805552","display_name":"Anders Szepessy","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Anders Szepessy","raw_affiliation_strings":["Department of Mathematics, Royal Institute of Technology, 100 44, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Royal Institute of Technology, 100 44, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064129060"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.502,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.66579745,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"2","issue":"3","first_page":"309","last_page":"332"},"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":0.5522000193595886,"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":0.5522000193595886,"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/T10320","display_name":"Neural Networks and Applications","score":0.1599999964237213,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.13750000298023224,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/random-fourier-features","display_name":"random Fourier features","score":0.9959999918937683},{"id":"https://openalex.org/keywords/neural-network-approximation","display_name":"neural network approximation","score":0.6389999985694885},{"id":"https://openalex.org/keywords/frequency-sampling","display_name":"frequency sampling","score":0.4269999861717224},{"id":"https://openalex.org/keywords/optimal-density","display_name":"optimal density","score":0.47600001096725464},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"supervised learning","score":0.6209999918937683},{"id":"https://openalex.org/keywords/high-dimensional-data","display_name":"high-dimensional data","score":0.6980000138282776},{"id":"https://openalex.org/keywords/approximation-error-minimization","display_name":"approximation error minimization","score":0.5720000267028809}],"concepts":[{"id":"https://openalex.org/C50742451","wikidata":"https://www.wikidata.org/wiki/Q1530388","display_name":"Equidistributed sequence","level":2,"score":0.9685554504394531},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5918048024177551},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.5847811698913574},{"id":"https://openalex.org/C2779557605","wikidata":"https://www.wikidata.org/wiki/Q9890","display_name":"Omega","level":2,"score":0.5377488136291504},{"id":"https://openalex.org/C207864730","wikidata":"https://www.wikidata.org/wiki/Q179467","display_name":"Fourier series","level":2,"score":0.4581214189529419},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.43681299686431885},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.4315890967845917},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41995272040367126},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.33966976404190063},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.32261955738067627},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.29204094409942627},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2335454821586609},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.08353617787361145}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3934/fods.2020014","doi":"https://doi.org/10.3934/fods.2020014","is_oa":true,"landing_page_url":"https://doi.org/10.3934/fods.2020014","pdf_url":null,"source":{"id":"https://openalex.org/S4210212798","display_name":"Foundations of Data Science","issn_l":"2639-8001","issn":["2639-8001"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","jufo-1","norway-1","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310315844","host_organization_name":"American Institute of Mathematical Sciences","host_organization_lineage":["https://openalex.org/P4310315844"],"host_organization_lineage_names":["American Institute of Mathematical Sciences"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foundations of Data Science","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2007.10683","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.10683","pdf_url":"https://arxiv.org/pdf/2007.10683","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":"mag:3045204686","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2007.10683.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2007.10683","doi":"https://doi.org/10.48550/arxiv.2007.10683","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.10683","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":"doi:10.3934/fods.2020014","doi":"https://doi.org/10.3934/fods.2020014","is_oa":true,"landing_page_url":"https://doi.org/10.3934/fods.2020014","pdf_url":null,"source":{"id":"https://openalex.org/S4210212798","display_name":"Foundations of Data Science","issn_l":"2639-8001","issn":["2639-8001"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","jufo-1","norway-1","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310315844","host_organization_name":"American Institute of Mathematical Sciences","host_organization_lineage":["https://openalex.org/P4310315844"],"host_organization_lineage_names":["American Institute of Mathematical Sciences"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foundations of Data Science","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2700844056","display_name":null,"funder_award_id":"W911NF1910243","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G2742944908","display_name":"Computational methods for ab initio molecular dynamics and partial differential equations in high dimension","funder_award_id":"2019-03725","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3045204686.pdf","grobid_xml":"https://content.openalex.org/works/W3045204686.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1855169650","https://openalex.org/W1989594010","https://openalex.org/W1995780830","https://openalex.org/W2008703230","https://openalex.org/W2030911724","https://openalex.org/W2044828368","https://openalex.org/W2047978125","https://openalex.org/W2125849100","https://openalex.org/W2144902422","https://openalex.org/W2166116275","https://openalex.org/W2224709232","https://openalex.org/W2914061777","https://openalex.org/W2938647293","https://openalex.org/W2953256123","https://openalex.org/W2963013450","https://openalex.org/W2963459001","https://openalex.org/W4236362309","https://openalex.org/W4320800818"],"related_works":["https://openalex.org/W4417410240","https://openalex.org/W2905119692","https://openalex.org/W4410903970","https://openalex.org/W7061902149","https://openalex.org/W4408160620","https://openalex.org/W2963477567","https://openalex.org/W2171155677","https://openalex.org/W2885554660","https://openalex.org/W2951783461","https://openalex.org/W2963459001"],"abstract_inverted_index":{"The":[0,30,46,111,148],"supervised":[1],"learning":[2],"problem":[3],"to":[4,97,104,116,119,137],"determine":[5],"a":[6,25,69,157],"neural":[7],"network":[8],"approximation":[9,80,140],"$":[10,17,36,52,58,64,73,94,100],"\\mathbb{R}^d\\ni":[11],"x\\mapsto\\sum_{k":[12],"=":[13],"1}^K\\hat\\beta_k":[14],"e^{{{\\mathrm{i}}}\\omega_k\\cdot":[15],"x}":[16],"with":[18,61],"one":[19],"hidden":[20],"layer":[21],"is":[22,133,150],"studied":[23],"as":[24,93],"random":[26,127],"Fourier":[27,31,128],"features":[28,129],"algorithm.":[29,147],"features,":[32],"i.e.,":[33],"the":[34,62,79,120,139,145],"frequencies":[35,51],"\\omega_k\\in\\mathbb{R}^d":[37],"$,":[38,54,60,67,75,96,102],"are":[39,114],"sampled":[40],"using":[41],"an":[42],"adaptive":[43,106],"Metropolis":[44,47],"sampler.":[45],"test":[48],"accepts":[49],"proposal":[50],"\\omega_k'":[53],"having":[55],"corresponding":[56],"amplitudes":[57,99,113],"\\hat\\beta_k'":[59],"probability":[63],"\\min\\big\\{1,":[65],"(|\\hat\\beta_k'|/|\\hat\\beta_k|)^{\\gamma}\\big\\}":[66],"for":[68,82,108,123],"certain":[70],"positive":[71],"parameter":[72],"{\\gamma}":[74],"determined":[76],"by":[77],"minimizing":[78],"error":[81],"given":[83],"computational":[84],"work.":[85],"This":[86],"adaptive,":[87],"non-parametric":[88],"stochastic":[89],"method":[90],"leads":[91],"asymptotically,":[92],"K\\to\\infty":[95],"equidistributed":[98,112],"|\\hat\\beta_k|":[101],"analogous":[103],"deterministic":[105],"algorithms":[107],"differential":[109],"equations.":[110],"shown":[115],"asymptotically":[117],"correspond":[118],"optimal":[121],"density":[122],"independent":[124],"samples":[125],"in":[126,135],"methods.":[130],"Numerical":[131],"evidence":[132],"provided":[134],"order":[136],"demonstrate":[138],"properties":[141],"and":[142,156],"efficiency":[143],"of":[144],"proposed":[146],"algorithm":[149],"tested":[151],"both":[152],"on":[153],"synthetic":[154],"data":[155],"real-world":[158],"high-dimensional":[159],"benchmark.":[160]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3045204686","counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-20T13:11:24.684918","created_date":"2020-07-29T00:00:00"}
