{"id":"https://openalex.org/W4414801960","doi":"https://doi.org/10.48550/arxiv.2506.00330","title":"Accurate Estimation of Mutual Information in High Dimensional Data","display_name":"Accurate Estimation of Mutual Information in High Dimensional Data","publication_year":2025,"publication_date":"2025-05-31","ids":{"openalex":"https://openalex.org/W4414801960","doi":"https://doi.org/10.48550/arxiv.2506.00330"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.00330","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2506.00330","pdf_url":"https://arxiv.org/pdf/2506.00330","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.00330","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093023319","display_name":"Eslam Abdelaleem","orcid":"https://orcid.org/0009-0006-9429-3589","observed_orcids":["https://orcid.org/0009-0006-9429-3589"]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdelaleem, Eslam","raw_affiliation_strings":["Department of Physics Emory University Atlanta , GA 30322 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Physics Emory University Atlanta , GA 30322 , USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030584398","display_name":"K. Michael Martini","orcid":"https://orcid.org/0000-0002-5946-1122","observed_orcids":["https://orcid.org/0000-0002-5946-1122"]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martini, K. Michael","raw_affiliation_strings":["Department of Physics Emory University Atlanta , GA 30322 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Physics Emory University Atlanta , GA 30322 , USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071388278","display_name":"Ilya M. Nemenman","orcid":"https://orcid.org/0000-0003-3024-4244","observed_orcids":["https://orcid.org/0000-0003-3024-4244"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nemenman, Ilya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.11079999804496765,"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/T10320","display_name":"Neural Networks and Applications","score":0.11079999804496765,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.10440000146627426,"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/T12261","display_name":"Statistical Mechanics and Entropy","score":0.0722000002861023,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mutual-information-estimation","display_name":"mutual information estimation","score":1.0},{"id":"https://openalex.org/keywords/high-dimensional-data","display_name":"high-dimensional data","score":0.722000002861023},{"id":"https://openalex.org/keywords/neural-network-estimator","display_name":"neural network estimator","score":0.6660000085830688},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"sample complexity","score":0.6970000267028809},{"id":"https://openalex.org/keywords/latent-dimensionality","display_name":"latent dimensionality","score":0.7580000162124634},{"id":"https://openalex.org/keywords/random-matrix-theory","display_name":"random matrix theory","score":0.9169999957084656},{"id":"https://openalex.org/keywords/bias-correction","display_name":"bias correction","score":0.8460000157356262},{"id":"https://openalex.org/keywords/confidence-intervals","display_name":"confidence intervals","score":0.9929999709129333},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.42100000381469727},{"id":"https://openalex.org/keywords/mnist","display_name":"MNIST","score":0.6449999809265137},{"id":"https://openalex.org/keywords/cifar","display_name":"CIFAR","score":0.9990000128746033}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.8726999759674072},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.6660000085830688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6065999865531921},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5680999755859375},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5126000046730042},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5015000104904175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44999998807907104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42969998717308044},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42730000615119934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4041000008583069},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26579999923706055},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.00330","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2506.00330","pdf_url":"https://arxiv.org/pdf/2506.00330","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.2506.00330","doi":"https://doi.org/10.48550/arxiv.2506.00330","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.00330","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:2506.00330","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2506.00330","pdf_url":"https://arxiv.org/pdf/2506.00330","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G257919420","display_name":"Bridging the Gap Between Particle-Based and Continuum Hydrodynamic Descriptions of Dusty Plasma","funder_award_id":"2409416","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2917891747","display_name":"Vocal motor control and sensorimotor learning - behavior, muscles, and neurons","funder_award_id":"R01NS084844","funder_id":"https://openalex.org/F4320337359","funder_display_name":"National Institute of Neurological Disorders and Stroke"},{"id":"https://openalex.org/G5753118818","display_name":"Dynamical Inference of Forces in Dusty Plasmas using Three-Dimensional Laser Sheet Tomography","funder_award_id":"2010524","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337359","display_name":"National Institute of Neurological Disorders and Stroke","ror":"https://ror.org/01s5ya894"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414801960.pdf","grobid_xml":"https://content.openalex.org/works/W4414801960.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2944503153","https://openalex.org/W7106664066","https://openalex.org/W4415428264","https://openalex.org/W4415797658","https://openalex.org/W4417323948","https://openalex.org/W2980313216","https://openalex.org/W3189092450","https://openalex.org/W3090062522","https://openalex.org/W3034696486","https://openalex.org/W7084597281"],"abstract_inverted_index":{"Mutual":[0],"information":[1],"(MI)":[2],"quantifies":[3],"statistical":[4,69,122],"dependence":[5],"between":[6],"variables":[7],"and":[8,38,100,127,146,185,210],"is":[9,78],"widely":[10],"used":[11],"across":[12],"scientific":[13,55],"disciplines,":[14],"yet":[15],"accurate":[16],"estimation":[17],"from":[18],"finite":[19],"data":[20],"remains":[21],"notoriously":[22],"difficult.":[23],"Common":[24],"approaches":[25],"fail":[26],"in":[27],"high-dimensional,":[28],"undersampled":[29],"regimes":[30],"($N":[31],"\\lesssim":[32],"K$)":[33],"typical":[34],"of":[35,136,176],"modern":[36],"experiments,":[37],"no":[39],"accepted":[40],"tests":[41],"exist":[42],"to":[43,206],"detect":[44],"when":[45,67],"neural":[46,60,118],"network-based":[47],"estimators":[48,62,119,154],"fail,":[49],"making":[50],"them":[51],"effectively":[52],"unusable":[53],"as":[54,166,168],"instruments.":[56],"We":[57,130,157],"show":[58],"that":[59,116,142],"MI":[61,150,216],"can":[63],"be":[64],"made":[65],"reliable":[66,215],"the":[68,82,90,159,171,203,220],"dependencies":[70],"admit":[71],"a":[72,94,113,133,190],"low-dimensional":[73],"latent":[74,83],"representation.":[75],"Sample":[76],"complexity":[77],"then":[79],"governed":[80],"by":[81],"dimensionality":[84],"$K_Z":[85],"\\ll":[86],"K$":[87],"rather":[88],"than":[89],"ambient":[91,221],"dimension":[92,223],"--":[93],"regime":[95],"shift":[96],"we":[97,111],"confirm":[98],"empirically":[99],"ground":[101],"theoretically":[102],"via":[103],"random":[104],"matrix":[105],"theory.":[106],"Building":[107],"on":[108,161,170,181,186,224],"this":[109],"insight,":[110],"develop":[112],"practical":[114],"protocol":[115,160,194],"provides":[117],"with":[120,189],"explicit":[121],"consistency":[123],"checks,":[124],"bias":[125,145],"correction,":[126],"confidence":[128,208],"intervals.":[129],"additionally":[131],"introduce":[132],"new":[134],"class":[135],"probabilistic":[137],"critics":[138],"(the":[139],"VSIB":[140],"family)":[141],"substantially":[143],"reduce":[144],"variance":[147],"at":[148],"higher":[149],"values":[151],"where":[152],"standard":[153,172],"break":[155],"down.":[156],"validate":[158],"synthetic":[162],"benchmarks":[163],"($K=500$,":[164],"$N$":[165],"low":[167],"$256$),":[169],"40-dataset":[173],"benchmark":[174],"suite":[175],"Czyz":[177],"et":[178],"al.":[179],"(2023),":[180],"noisy":[182],"MNIST":[183],"($K=784$),":[184],"CIFAR-10/100":[187],"($K=3072$)":[188],"ResNet-20":[191],"backbone.":[192],"Our":[193],"consistently":[195],"matches":[196],"or":[197],"exceeds":[198],"existing":[199],"methods":[200],"while":[201],"being":[202],"only":[204],"approach":[205],"report":[207],"intervals":[209],"flag":[211],"unreliable":[212],"estimates,":[213],"achieving":[214],"detection":[217],"well":[218],"below":[219],"pixel":[222],"real":[225],"images.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}