{"id":"https://openalex.org/W4289713170","doi":"https://doi.org/10.1109/isit50566.2022.9834412","title":"Universal Compression of Large Alphabets with Constrained Compressors","display_name":"Universal Compression of Large Alphabets with Constrained Compressors","publication_year":2022,"publication_date":"2022-06-26","ids":{"openalex":"https://openalex.org/W4289713170","doi":"https://doi.org/10.1109/isit50566.2022.9834412"},"language":"en","primary_location":{"id":"doi:10.1109/isit50566.2022.9834412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834412","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"2022 IEEE International Symposium on Information Theory (ISIT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086990183","display_name":"Hao Lou","orcid":"https://orcid.org/0000-0002-6133-2987"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao Lou","raw_affiliation_strings":["University of Virginia,Electrical and Computer Engineering,VA,USA","Electrical and Computer Engineering, University of Virginia, VA, USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia,Electrical and Computer Engineering,VA,USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Electrical and Computer Engineering, University of Virginia, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011621481","display_name":"Farzad Farnoud","orcid":"https://orcid.org/0000-0002-8684-4487"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farzad Farnoud","raw_affiliation_strings":["University of Virginia,Electrical and Computer Engineering,VA,USA","Electrical and Computer Engineering, University of Virginia, VA, USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia,Electrical and Computer Engineering,VA,USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Electrical and Computer Engineering, University of Virginia, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086990183"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0693274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.9983999729156494,"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/T11567","display_name":"semigroups and automata theory","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7419816255569458},{"id":"https://openalex.org/keywords/alphabet","display_name":"Alphabet","score":0.6012828946113586},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5682621002197266},{"id":"https://openalex.org/keywords/gas-compressor","display_name":"Gas compressor","score":0.5528872013092041},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.530903697013855},{"id":"https://openalex.org/keywords/integer","display_name":"Integer (computer science)","score":0.5249985456466675},{"id":"https://openalex.org/keywords/huffman-coding","display_name":"Huffman coding","score":0.49277785420417786},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.49274829030036926},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.478158563375473},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.46091464161872864},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4537998139858246},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.44389608502388},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.43200838565826416},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.4100074768066406},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.39321139454841614},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.3931349515914917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.07476469874382019}],"concepts":[{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7419816255569458},{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.6012828946113586},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5682621002197266},{"id":"https://openalex.org/C131097465","wikidata":"https://www.wikidata.org/wiki/Q178898","display_name":"Gas compressor","level":2,"score":0.5528872013092041},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.530903697013855},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.5249985456466675},{"id":"https://openalex.org/C46900642","wikidata":"https://www.wikidata.org/wiki/Q2647","display_name":"Huffman coding","level":3,"score":0.49277785420417786},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49274829030036926},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.478158563375473},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.46091464161872864},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4537998139858246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.44389608502388},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.43200838565826416},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.4100074768066406},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.39321139454841614},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3931349515914917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.07476469874382019},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit50566.2022.9834412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834412","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"2022 IEEE International Symposium on Information Theory (ISIT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W69510097","https://openalex.org/W200233886","https://openalex.org/W1502929163","https://openalex.org/W1576397915","https://openalex.org/W1971161599","https://openalex.org/W2013458156","https://openalex.org/W2022249568","https://openalex.org/W2049724793","https://openalex.org/W2096798913","https://openalex.org/W2105570447","https://openalex.org/W2120127941","https://openalex.org/W2123744935","https://openalex.org/W2132119275","https://openalex.org/W2148418648","https://openalex.org/W2475932436","https://openalex.org/W2751862591","https://openalex.org/W2944693735","https://openalex.org/W2998583855","https://openalex.org/W3080836056","https://openalex.org/W3197696349","https://openalex.org/W6602837329","https://openalex.org/W6608138927","https://openalex.org/W6634463810","https://openalex.org/W6681754916","https://openalex.org/W6782911655","https://openalex.org/W7038906009"],"related_works":["https://openalex.org/W1557642114","https://openalex.org/W1762028264","https://openalex.org/W2948148442","https://openalex.org/W2461250372","https://openalex.org/W2394342941","https://openalex.org/W2169853506","https://openalex.org/W2547124190","https://openalex.org/W2350586049","https://openalex.org/W2385628723","https://openalex.org/W3154960554"],"abstract_inverted_index":{"Over":[0],"unknown,":[1],"possibly":[2],"large,":[3],"alphabets,":[4],"one":[5],"approach":[6],"for":[7,85,94],"compressing":[8],"sequences":[9],"is":[10,80,120,147],"to":[11,152],"separately":[12],"convey":[13],"their":[14],"symbols":[15,26,136],"and":[16,82,109,150],"patterns":[17,33,70,95],"(sequences":[18],"of":[19,50,52,69,77,103,133],"integers":[20],"representing":[21],"orders":[22],"in":[23,137,156],"which":[24],"the":[25,48,106,121,125,131,138,157],"appear).":[27],"It":[28],"has":[29],"been":[30],"shown":[31,151],"that":[32,46,93,127],"generated":[34,96],"by":[35,57,97],"i.i.d.":[36,98],"sources":[37,99],"can":[38],"be":[39],"compressed":[40],"with":[41,59],"diminishing":[42],"redundancy":[43,155],"using":[44,71],"compressors":[45,72,79,128],"know":[47,130],"number":[49,132],"occurrences":[51],"each":[53],"integer":[54,135],"symbol.":[55],"Motivated":[56],"applications":[58],"resource":[60],"restrictions,":[61],"e.g.,":[62],"data":[63],"deduplication,":[64],"we":[65],"study":[66],"universal":[67],"compression":[68],"under":[73,124],"constraints.":[74],"A":[75,140],"characterization":[76],"constrained":[78],"given":[81],"general":[83],"results":[84],"computing":[86],"redundancies":[87,111],"are":[88,112],"derived.":[89],"We":[90],"also":[91,148],"show":[92],"over":[100],"an":[101],"alphabet":[102],"size":[104],"k,":[105],"per-symbol":[107],"average-":[108],"worst-case":[110],"at":[113],"least":[114],"\u0398(log(min(k,":[115],"n/":[116],"logn)))":[117],"bits":[118],"(n":[119],"sequence":[122],"length),":[123],"constraint":[126,146],"only":[129],"distinct":[134],"pattern.":[139],"simple":[141],"sequential":[142],"compressor":[143],"satisfying":[144],"this":[145,154],"analyzed":[149],"achieve":[153],"first":[158],"order":[159],"term.":[160]},"counts_by_year":[],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}