{"id":"https://openalex.org/W4289655031","doi":"https://doi.org/10.1109/isit50566.2022.9834837","title":"Efficient Representation of Large-Alphabet Probability Distributions via Arcsinh-Compander","display_name":"Efficient Representation of Large-Alphabet Probability Distributions via Arcsinh-Compander","publication_year":2022,"publication_date":"2022-06-26","ids":{"openalex":"https://openalex.org/W4289655031","doi":"https://doi.org/10.1109/isit50566.2022.9834837"},"language":"en","primary_location":{"id":"doi:10.1109/isit50566.2022.9834837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834837","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/A5006903412","display_name":"Aviv Adler","orcid":"https://orcid.org/0000-0003-3698-7639"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aviv Adler","raw_affiliation_strings":["EECS (MIT),Cambridge,MA,USA","EECS (MIT), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"EECS (MIT),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210110987"]},{"raw_affiliation_string":"EECS (MIT), Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071582967","display_name":"Jennifer Tang","orcid":"https://orcid.org/0000-0002-8369-7901"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jennifer Tang","raw_affiliation_strings":["EECS (MIT),Cambridge,MA,USA","EECS (MIT), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"EECS (MIT),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210110987"]},{"raw_affiliation_string":"EECS (MIT), Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031031216","display_name":"Yury Polyanskiy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yury Polyanskiy","raw_affiliation_strings":["EECS (MIT),Cambridge,MA,USA","EECS (MIT), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"EECS (MIT),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210110987"]},{"raw_affiliation_string":"EECS (MIT), Cambridge, MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006903412"],"corresponding_institution_ids":["https://openalex.org/I4210110987"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0674193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"162","last_page":"167"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994000196456909,"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":0.9994000196456909,"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9973999857902527,"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/combinatorics","display_name":"Combinatorics","score":0.498659610748291},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.41765788197517395},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.41717129945755005},{"id":"https://openalex.org/keywords/alphabet","display_name":"Alphabet","score":0.41525495052337646},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3907414376735687},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34928473830223083}],"concepts":[{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.498659610748291},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.41765788197517395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41717129945755005},{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.41525495052337646},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3907414376735687},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34928473830223083},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit50566.2022.9834837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834837","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1576475658","https://openalex.org/W1686946872","https://openalex.org/W2001968606","https://openalex.org/W2004003571","https://openalex.org/W2018040777","https://openalex.org/W2068071220","https://openalex.org/W2085854859","https://openalex.org/W2089419199","https://openalex.org/W2103723258","https://openalex.org/W2127314673","https://openalex.org/W2132512523","https://openalex.org/W2138570191","https://openalex.org/W2142228262","https://openalex.org/W2171052652","https://openalex.org/W3198737060","https://openalex.org/W4288346545","https://openalex.org/W4313598801","https://openalex.org/W6637108112","https://openalex.org/W6675471587","https://openalex.org/W6680765659","https://openalex.org/W6763653508","https://openalex.org/W7018288791"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2051487156","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027","https://openalex.org/W2600246793"],"abstract_inverted_index":{"A":[0,46],"number":[1],"of":[2,20,24,75,111,120,214,246],"engineering":[3],"and":[4,9,62,102,177,181,195,229],"scientific":[5],"problems":[6],"require":[7],"representing":[8],"manipulating":[10],"probability":[11],"distributions":[12],"over":[13],"large":[14],"alphabets,":[15,108],"which":[16],"we":[17,188],"may":[18],"think":[19],"as":[21,258,262],"long":[22],"vectors":[23],"reals":[25],"summing":[26],"to":[27,35,50,65,87,123,135,155],"1.":[28],"In":[29],"some":[30],"cases":[31],"it":[32],"is":[33,49,257],"required":[34],"represent":[36],"such":[37],"a":[38,72,115,191,211,226,233],"vector":[39],"with":[40],"only":[41],"b":[42,99,230],"bits":[43],"per":[44],"entry.":[45],"natural":[47],"choice":[48],"partition":[51],"the":[52,109,143,198,238,242,247,254,263],"interval":[53],"[0,1]":[54],"into":[55],"2":[56,216],"<sup":[57,104,125,129,147,151,157,161,217,221],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[58,105,126,130,148,152,158,162,218,222],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">b</sup>":[59],"uniform":[60,249,264],"bins":[61],"quantize":[63],"entries":[64],"each":[66],"bin":[67],"independently.":[68],"We":[69],"show":[70,196],"that":[71,197,253],"minor":[73],"modification":[74],"this":[76],"procedure":[77],"\u2013":[78,89],"applying":[79],"an":[80,91],"entrywise":[81],"non-linear":[82],"function":[83],"(compander)":[84],"f(x)":[85],"prior":[86],"quantization":[88,94],"yields":[90],"extremely":[92],"effective":[93],"method.":[95],"For":[96],"example,":[97],"for":[98,169,182,225,237,260,266],"=":[100],"8(16)":[101],"10":[103,124,146,156],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">5</sup>":[106],"-sized":[107],"quality":[110],"representation":[112],"improves":[113,142],"from":[114,145],"loss":[116,144,213,240],"(under":[117],"KL":[118],"divergence)":[119],"0.5(0.1)":[121],"bits/entry":[122],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u22124</sup>":[127,159],"(10":[128,150,160],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u22129</sup>":[131,163],")":[132,154,164],"bits/entry.":[133,165],"Compared":[134],"floating":[136],"point":[137],"representations,":[138],"our":[139],"compander":[140,199],"method":[141],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u22121</sup>":[149],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u22126</sup>":[153],"These":[166],"numbers":[167],"hold":[168],"both":[170],"real-world":[171],"data":[172],"(word":[173],"frequencies":[174],"in":[175],"books":[176],"DNA":[178],"k-mer":[179],"counts)":[180],"synthetic":[183],"randomly":[184],"generated":[185],"distributions.":[186],"Theoretically,":[187],"set":[189],"up":[190],"minimax":[192,235],"optimality":[193,245],"criterion":[194,236],"$f(x)":[200],"\\propto":[201],"\\operatorname{ArcSinh}":[202],"(\\sqrt":[203],"{(1/2)(K\\log":[204],"K)x}":[205],")$":[206],"achieves":[207],"near-optimal":[208],"performance,":[209],"attaining":[210],"KL-quantization":[212],"\u224d":[215],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u22122b</sup>":[219],"log":[220],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[223],"K":[224],"K-letter":[227],"alphabet":[228],"\u2192\u221e.":[231],"Interestingly,":[232],"similar":[234],"quadratic":[239,267],"on":[241],"hypercube":[243],"shows":[244],"standard":[248],"quantizer.":[250],"This":[251],"suggests":[252],"ArcSinh":[255],"quantizer":[256,265],"fundamental":[259],"KL-distortion":[261],"distortion.":[268]},"counts_by_year":[],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}