{"id":"https://openalex.org/W3043827856","doi":"https://doi.org/10.1109/tit.2020.3044622","title":"On the Sample Complexity of HGR Maximal Correlation Functions for Large Datasets","display_name":"On the Sample Complexity of HGR Maximal Correlation Functions for Large Datasets","publication_year":2020,"publication_date":"2020-12-14","ids":{"openalex":"https://openalex.org/W3043827856","doi":"https://doi.org/10.1109/tit.2020.3044622","mag":"3043827856"},"language":"en","primary_location":{"id":"doi:10.1109/tit.2020.3044622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2020.3044622","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.00393","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shao-Lun Huang","orcid":"https://orcid.org/0000-0001-7020-5456"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shao-Lun Huang","raw_affiliation_strings":["Data Science and Information Technology Research Center, Tsinghua\u2013Berkeley Shenzhen Institute, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-7020-5456","affiliations":[{"raw_affiliation_string":"Data Science and Information Technology Research Center, Tsinghua\u2013Berkeley Shenzhen Institute, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiangxiang Xu","orcid":"https://orcid.org/0000-0002-4178-0934"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangxiang Xu","raw_affiliation_strings":["Data Science and Information Technology Research Center, Tsinghua\u2013Berkeley Shenzhen Institute, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-4178-0934","affiliations":[{"raw_affiliation_string":"Data Science and Information Technology Research Center, Tsinghua\u2013Berkeley Shenzhen Institute, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114105"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.09336833,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"67","issue":"3","first_page":"1951","last_page":"1980"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.20720000565052032,"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"}},"topics":[{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.20720000565052032,"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"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.18619999289512634,"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":0.1467999964952469,"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/sample-complexity","display_name":"Sample complexity","score":0.7409999966621399},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.6541000008583069},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5843999981880188},{"id":"https://openalex.org/keywords/exponent","display_name":"Exponent","score":0.5195000171661377},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5159000158309937},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.40630000829696655},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4009999930858612},{"id":"https://openalex.org/keywords/mean-squared-prediction-error","display_name":"Mean squared prediction error","score":0.33709999918937683},{"id":"https://openalex.org/keywords/approximation-error","display_name":"Approximation error","score":0.3163999915122986}],"concepts":[{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.7409999966621399},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6991000175476074},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.6541000008583069},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5843999981880188},{"id":"https://openalex.org/C2780388253","wikidata":"https://www.wikidata.org/wiki/Q5421508","display_name":"Exponent","level":2,"score":0.5195000171661377},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5159000158309937},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49549999833106995},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3296999931335449},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3287999927997589},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3075000047683716},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.30090001225471497},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.2816999852657318},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.27950000762939453},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2745000123977661},{"id":"https://openalex.org/C163018871","wikidata":"https://www.wikidata.org/wiki/Q1302587","display_name":"Cross-correlation","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C145242015","wikidata":"https://www.wikidata.org/wiki/Q774123","display_name":"Approximation theory","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C186215838","wikidata":"https://www.wikidata.org/wiki/Q772232","display_name":"Conditional expectation","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25369998812675476},{"id":"https://openalex.org/C181243257","wikidata":"https://www.wikidata.org/wiki/Q1693522","display_name":"Sample mean and sample covariance","level":3,"score":0.2531000077724457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.25220000743865967},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tit.2020.3044622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2020.3044622","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1907.00393","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.00393","pdf_url":"https://arxiv.org/pdf/1907.00393","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.00393","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.00393","pdf_url":"https://arxiv.org/pdf/1907.00393","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6483256435","display_name":null,"funder_award_id":"61807021","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":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1995228946","https://openalex.org/W2000065263","https://openalex.org/W2003776291","https://openalex.org/W2004026774","https://openalex.org/W2018582985","https://openalex.org/W2039103602","https://openalex.org/W2054141820","https://openalex.org/W2095841525","https://openalex.org/W2107327484","https://openalex.org/W2163922914","https://openalex.org/W2170862660","https://openalex.org/W2556383977","https://openalex.org/W2742980034","https://openalex.org/W2963767133","https://openalex.org/W2976504920","https://openalex.org/W2992716730","https://openalex.org/W3004997939","https://openalex.org/W3006229350","https://openalex.org/W4229706427","https://openalex.org/W4236362309","https://openalex.org/W4248624814","https://openalex.org/W4293404332","https://openalex.org/W6680140577","https://openalex.org/W6770506162","https://openalex.org/W6780193051","https://openalex.org/W6807958671"],"related_works":[],"abstract_inverted_index":{"The":[0],"Hirschfeld-Gebelein-R\u00e9nyi":[1],"(HGR)":[2],"maximal":[3,30,59,113],"correlation":[4,31,60,114],"and":[5,67,78,152],"the":[6,23,28,34,54,58,64,68,72,84,88,92,102,106,111,117,124,135,161,165,169],"corresponding":[7],"functions":[8,32,61,69,115],"have":[9],"been":[10],"shown":[11],"useful":[12],"in":[13,143],"many":[14],"machine":[15],"learning":[16,55,80,93,110,145,166],"scenarios.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21,47,82,96,133],"study":[22],"sample":[24,107],"complexity":[25,108],"of":[26,91,109,141,164],"estimating":[27],"HGR":[29,112],"by":[33,116],"alternating":[35],"conditional":[36],"expectation":[37],"(ACE)":[38],"algorithm":[39,119],"using":[40,123],"training":[41],"samples":[42,142],"from":[43,63,71],"large":[44,100],"datasets.":[45],"Specifically,":[46],"develop":[48],"a":[49,147],"mathematical":[50],"framework":[51],"to":[52,159,174],"characterize":[53],"errors":[56],"between":[57],"computed":[62],"true":[65],"distribution,":[66],"estimated":[70],"ACE":[73,118],"algorithm.":[74],"For":[75],"both":[76],"supervised":[77],"semi-supervised":[79,144],"scenarios,":[81],"establish":[83],"analytical":[85],"expressions":[86],"for":[87,99,105,138],"error":[89,126,162],"exponents":[90],"errors.":[94],"Furthermore,":[95],"demonstrate":[97],"that":[98],"datasets,":[101],"upper":[103],"bounds":[104],"can":[120],"be":[121],"expressed":[122],"established":[125],"exponents.":[127],"Moreover,":[128],"with":[129,146],"our":[130,176],"theoretical":[131,177],"results,":[132],"investigate":[134],"sampling":[136,149,155],"strategy":[137,156],"different":[139],"types":[140],"total":[148],"budget":[150],"constraint,":[151],"an":[153],"optimal":[154],"is":[157],"developed":[158],"maximize":[160],"exponent":[163],"error.":[167],"Finally,":[168],"numerical":[170],"simulations":[171],"are":[172],"presented":[173],"support":[175],"results.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2020-07-29T00:00:00"}