{"id":"https://openalex.org/W2996736304","doi":"https://doi.org/10.3390/e22010007","title":"Pareto-Optimal Data Compression for Binary Classification Tasks","display_name":"Pareto-Optimal Data Compression for Binary Classification Tasks","publication_year":2019,"publication_date":"2019-12-19","ids":{"openalex":"https://openalex.org/W2996736304","doi":"https://doi.org/10.3390/e22010007","mag":"2996736304","pmid":"https://pubmed.ncbi.nlm.nih.gov/33285782"},"language":"en","primary_location":{"id":"doi:10.3390/e22010007","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e22010007","pdf_url":"https://www.mdpi.com/1099-4300/22/1/7/pdf?version=1578446932","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1099-4300/22/1/7/pdf?version=1578446932","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Max Tegmark","orcid":"https://orcid.org/0000-0001-7670-7190"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Max Tegmark","raw_affiliation_strings":["Department of Physics, MIT Kavli Institute &amp; Center for Brains, Minds &amp; Machines, Massachusetts Institute of Technology, Cambridge, MA 02139, USA"],"affiliations":[{"raw_affiliation_string":"Department of Physics, MIT Kavli Institute &amp; Center for Brains, Minds &amp; Machines, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":null,"display_name":"Tailin Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tailin Wu","raw_affiliation_strings":["Department of Physics, MIT Kavli Institute &amp; Center for Brains, Minds &amp; Machines, Massachusetts Institute of Technology, Cambridge, MA 02139, USA"],"affiliations":[{"raw_affiliation_string":"Department of Physics, MIT Kavli Institute &amp; Center for Brains, Minds &amp; Machines, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":1.5997,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85831918,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"22","issue":"1","first_page":"7","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.3578000068664551,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.3578000068664551,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.1257999986410141,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.09220000356435776,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5824000239372253},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5648999810218811},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5360000133514404},{"id":"https://openalex.org/keywords/conditional-entropy","display_name":"Conditional entropy","score":0.5091999769210815},{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.5069000124931335},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48420000076293945},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4138000011444092},{"id":"https://openalex.org/keywords/information-theory","display_name":"Information theory","score":0.41200000047683716},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.40869998931884766},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.3986000120639801}],"concepts":[{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5824000239372253},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5648999810218811},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5360000133514404},{"id":"https://openalex.org/C101721835","wikidata":"https://www.wikidata.org/wiki/Q813908","display_name":"Conditional entropy","level":3,"score":0.5091999769210815},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.508899986743927},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.5069000124931335},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42570000886917114},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.4223000109195709},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.414000004529953},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40639999508857727},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C193828747","wikidata":"https://www.wikidata.org/wiki/Q864118","display_name":"Binary image","level":4,"score":0.3880999982357025},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.36079999804496765},{"id":"https://openalex.org/C2779190172","wikidata":"https://www.wikidata.org/wiki/Q4913888","display_name":"Binary data","level":3,"score":0.35089999437332153},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.33550000190734863},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3249000012874603},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.30649998784065247},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C44415725","wikidata":"https://www.wikidata.org/wiki/Q4913893","display_name":"Binary entropy function","level":3,"score":0.30090001225471497},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C197855036","wikidata":"https://www.wikidata.org/wiki/Q380172","display_name":"Binary tree","level":2,"score":0.2696000039577484}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.3390/e22010007","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e22010007","pdf_url":"https://www.mdpi.com/1099-4300/22/1/7/pdf?version=1578446932","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1908.08961","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.08961","pdf_url":"https://arxiv.org/pdf/1908.08961","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"},{"id":"pmid:33285782","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33285782","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:dspace.mit.edu:1721.1/125546","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/125546","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Multidisciplinary Digital Publishing Institute","raw_type":"http://purl.org/eprint/type/JournalArticle"},{"id":"pmh:oai:mdpi.com:/1099-4300/22/1/7/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/e22010007","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Entropy","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:7516503","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7516503","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Entropy (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/e22010007","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e22010007","pdf_url":"https://www.mdpi.com/1099-4300/22/1/7/pdf?version=1578446932","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7160521497","display_name":null,"funder_award_id":"0322","funder_id":"https://openalex.org/F4320327239","funder_display_name":"Templeton World Charity Foundation"}],"funders":[{"id":"https://openalex.org/F4320327239","display_name":"Templeton World Charity Foundation","ror":"https://ror.org/00x0z1472"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2996736304.pdf","grobid_xml":"https://content.openalex.org/works/W2996736304.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1980432290","https://openalex.org/W2004026774","https://openalex.org/W2025341678","https://openalex.org/W2025768430","https://openalex.org/W2029236670","https://openalex.org/W2148986322","https://openalex.org/W2194775991","https://openalex.org/W2294798173","https://openalex.org/W2398870399","https://openalex.org/W2797548502","https://openalex.org/W2880214242","https://openalex.org/W2920204733","https://openalex.org/W2960183474","https://openalex.org/W2962702487","https://openalex.org/W2963343988","https://openalex.org/W6677621685","https://openalex.org/W6752757957","https://openalex.org/W6758409858","https://openalex.org/W6785661282","https://openalex.org/W6898611122"],"related_works":[],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,12,35,176,206,263,293,359],"lossy":[3],"data":[4,14],"compression":[5],"is":[6,82,183],"to":[7,52,314,351],"reduce":[8],"the":[9,40,66,76,96,103,201,251,256,264,273,315,357],"storage":[10],"cost":[11],"a":[13,47,54,90,115,124,139,172,186,219,247,261,290],"set":[15],"<i>X</i>":[16,38,118,182],"while":[17,75],"retaining":[18,191],"as":[19,22,327],"much":[20],"information":[21,42,68,193,266],"possible":[23],"about":[24,43],"something":[25],"(<i>Y</i>)":[26],"that":[27,64,154,194,249,272,336,344],"you":[28],"care":[29],"about.":[30],"For":[31,200],"example,":[32,170],"what":[33],"aspects":[34],"an":[36,328],"image":[37,181,331],"contain":[39],"most":[41,274],"whether":[44],"it":[45,323],"depicts":[46],"cat?":[48],"Mathematically,":[49],"this":[50,278,312],"corresponds":[51],"finding":[53],"mapping":[55,94],"X":[56,62,145,164],"\u2192":[57],"Z":[58,71,80,222,285],"\u2261":[59],"f":[60,143],"(":[61,70,79,144,156,163,226,284],")":[63,74,81,146,160,167,228,288],"maximizes":[65],"mutual":[67],"I":[69,155,162,283],",":[72,130,132,158,165,232,234,286,298,300],"Y":[73,126,159,166,287],"entropy":[77,107],"H":[78],"kept":[83],"below":[84],"some":[85],"fixed":[86,291],"threshold.":[87],"We":[88,111,270,310,334],"present":[89],"new":[91],"method":[92,313],"for":[93,99,169,171,289],"out":[95,255],"Pareto":[97,258,338],"frontier":[98,279],"classification":[100,174],"tasks,":[101],"reflecting":[102],"tradeoff":[104],"between":[105,353],"retained":[106],"and":[108,178,318,343],"class":[109,125],"information.":[110],"first":[112],"show":[113,211],"how":[114,212,322],"random":[116],"variable":[117,221],"(an":[119],"image,":[120],"say)":[121],"drawn":[122],"from":[123,198],"\u2208":[127,147,229],"{":[128,230],"1":[129,151,231],"\u2026":[131,233,301],"n":[133,149,202],"}":[134,237],"can":[135,214,303,324],"be":[136,215,305,325],"distilled":[137],"into":[138,185,218,241],"vector":[140],"W":[141,157,227],"=":[142,161,203,223,296],"R":[148],"-":[150],"losslessly,":[152],"so":[153],";":[168],"binary":[173,207],"task":[175],"cats":[177,197],"dogs,":[179],"each":[180],"mapped":[184],"single":[187],"real":[188],"number":[189,292,358],"<i>W</i>":[190,213,240],"all":[192],"helps":[195],"distinguish":[196],"dogs.":[199],"2":[204,297],"case":[205],"classification,":[208],"we":[209],"then":[210],"further":[216],"compressed":[217],"discrete":[220,265],"g":[224],"\u03b2":[225,236,243,253],"m":[235,242,295],"by":[238],"binning":[239],"bins,":[244],"in":[245],"such":[246],"way":[248],"varying":[250],"parameter":[252],"sweeps":[254],"full":[257],"frontier,":[259],"solving":[260],"generalization":[262],"bottleneck":[267],"(DIB)":[268],"problem.":[269],"argue":[271],"interesting":[275],"points":[276],"on":[277],"are":[280,340],"\"corners\"":[281],"maximizing":[282],"bins":[294],"3":[299],"which":[302],"conveniently":[304],"found":[306],"without":[307],"multiobjective":[308],"optimization.":[309],"apply":[311],"CIFAR-10,":[316],"MNIST":[317],"Fashion-MNIST":[319],"datasets,":[320],"illustrating":[321],"interpreted":[326],"information-theoretically":[329],"optimal":[330],"clustering":[332],"algorithm.":[333],"find":[335],"these":[337,354],"frontiers":[339],"not":[341],"concave,":[342],"recently":[345],"reported":[346],"DIB":[347],"phase":[348],"transitions":[349,352],"correspond":[350],"corners,":[355],"changing":[356],"clusters.":[360]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2019-12-26T00:00:00"}