{"id":"https://openalex.org/W4321195183","doi":"https://doi.org/10.1109/jsait.2023.3245417","title":"Compressing Multisets With Large Alphabets","display_name":"Compressing Multisets With Large Alphabets","publication_year":2022,"publication_date":"2022-12-01","ids":{"openalex":"https://openalex.org/W4321195183","doi":"https://doi.org/10.1109/jsait.2023.3245417"},"language":"en","primary_location":{"id":"doi:10.1109/jsait.2023.3245417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsait.2023.3245417","pdf_url":null,"source":{"id":"https://openalex.org/S4210211895","display_name":"IEEE Journal on Selected Areas in Information Theory","issn_l":"2641-8770","issn":["2641-8770"],"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 Journal on Selected Areas in Information Theory","raw_type":"journal-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/A5089038476","display_name":"Daniel Severo","orcid":"https://orcid.org/0000-0003-0472-5300"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Daniel Severo","raw_affiliation_strings":["Meta AI, New York, NY, USA","University of Toronto, Canada","Vector Institute for AI, Canada"],"raw_orcid":"https://orcid.org/0000-0003-0472-5300","affiliations":[{"raw_affiliation_string":"Meta AI, New York, NY, USA","institution_ids":[]},{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Vector Institute for AI, Canada","institution_ids":["https://openalex.org/I4210127509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058841326","display_name":"James T. Townsend","orcid":"https://orcid.org/0000-0002-1715-0588"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"James Townsend","raw_affiliation_strings":["Amsterdam Machine Learning Lab, University of Amsterdam, Amsterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amsterdam Machine Learning Lab, University of Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046253142","display_name":"Ashish Khisti","orcid":"https://orcid.org/0000-0002-2331-8965"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ashish Khisti","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2331-8965","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031533607","display_name":"Alireza Makhzani","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alireza Makhzani","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada","Vector Institute for AI, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Vector Institute for AI, Canada","institution_ids":["https://openalex.org/I4210127509"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058031547","display_name":"Karen Ullrich","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karen Ullrich","raw_affiliation_strings":["Meta AI, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI, New York, NY, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.348,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66305443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"3","issue":"4","first_page":"605","last_page":"615"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9966999888420105,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9883000254631042,"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/multiset","display_name":"Multiset","score":0.9183571338653564},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.8830872774124146},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7323818206787109},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5134021043777466},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.509283185005188},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.49461790919303894},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4905082583427429},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.45559242367744446},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23898354172706604},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.2086816430091858},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17574629187583923}],"concepts":[{"id":"https://openalex.org/C2779623528","wikidata":"https://www.wikidata.org/wiki/Q864377","display_name":"Multiset","level":2,"score":0.9183571338653564},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.8830872774124146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7323818206787109},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5134021043777466},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.509283185005188},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49461790919303894},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4905082583427429},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.45559242367744446},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23898354172706604},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.2086816430091858},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17574629187583923},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/jsait.2023.3245417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsait.2023.3245417","pdf_url":null,"source":{"id":"https://openalex.org/S4210211895","display_name":"IEEE Journal on Selected Areas in Information Theory","issn_l":"2641-8770","issn":["2641-8770"],"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 Journal on Selected Areas in Information Theory","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W52127214","https://openalex.org/W172574161","https://openalex.org/W1874489690","https://openalex.org/W1933799648","https://openalex.org/W1972027649","https://openalex.org/W1980628172","https://openalex.org/W1982054392","https://openalex.org/W1994211684","https://openalex.org/W2011797301","https://openalex.org/W2066354072","https://openalex.org/W2101208289","https://openalex.org/W2112038332","https://openalex.org/W2169742131","https://openalex.org/W2569540185","https://openalex.org/W2905634902","https://openalex.org/W2945490368","https://openalex.org/W2963995133","https://openalex.org/W3001953680","https://openalex.org/W3139404160","https://openalex.org/W3160501684","https://openalex.org/W3171483544","https://openalex.org/W3183608192","https://openalex.org/W3217574455","https://openalex.org/W4297824565","https://openalex.org/W4300996320","https://openalex.org/W6639362626","https://openalex.org/W6640455647","https://openalex.org/W6756754865","https://openalex.org/W6762805079","https://openalex.org/W6771628455","https://openalex.org/W6772891471","https://openalex.org/W6790313041","https://openalex.org/W6792133088","https://openalex.org/W6793869185","https://openalex.org/W7055007012"],"related_works":["https://openalex.org/W2753132265","https://openalex.org/W2095407248","https://openalex.org/W1997714924","https://openalex.org/W2129190845","https://openalex.org/W4389045637","https://openalex.org/W1994209155","https://openalex.org/W1971210268","https://openalex.org/W4384300015","https://openalex.org/W2100712766","https://openalex.org/W2054979592"],"abstract_inverted_index":{"Current":[0],"methods":[1],"which":[2,106],"compress":[3,60,89],"multisets":[4,61,115],"at":[5,65,130],"an":[6,46,66],"optimal":[7,67],"rate":[8],"have":[9],"computational":[10,70],"complexity":[11,48,71],"that":[12,50],"scales":[13],"linearly":[14],"with":[15,69,109],"alphabet":[16,75],"size,":[17],"making":[18],"them":[19],"too":[20],"slow":[21],"to":[22,32,59,81],"be":[23],"practical":[24],"in":[25,43,53],"many":[26],"real-world":[27],"settings.":[28],"We":[29,99],"show":[30],"how":[31],"convert":[33],"a":[34,90,94],"compression":[35,113],"algorithm":[36],"for":[37,41,45,125],"sequences":[38],"into":[39],"one":[40],"multisets,":[42],"exchange":[44],"additional":[47],"term":[49],"is":[51,80,128],"quasi-linear":[52],"sequence":[54],"length.":[55],"This":[56],"allows":[57],"us":[58],"of":[62,114,116],"exchangeable":[63],"symbols":[64],"rate,":[68],"decoupled":[72],"from":[73],"the":[74,84,101],"size.":[76],"The":[77],"key":[78],"insight":[79],"avoid":[82],"encoding":[83],"multiset":[85],"directly,":[86],"and":[87,118],"instead":[88],"proxy":[91],"sequence,":[92],"using":[93],"technique":[95],"called":[96],"bits-back":[97],"coding.":[98],"demonstrate":[100],"method":[102],"experimentally":[103],"on":[104],"tasks":[105],"are":[107],"intractable":[108],"previous":[110],"optimal-rate":[111],"methods:":[112],"images":[117],"JavaScript":[119],"Object":[120],"Notation":[121],"(JSON)":[122],"files.":[123],"Code":[124],"our":[126],"experiments":[127],"available":[129],"https://github.com/facebookresearch/multiset-compression.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2023-02-18T00:00:00"}