{"id":"https://openalex.org/W3198699721","doi":"https://doi.org/10.1109/isit45174.2021.9517991","title":"Two-sample Testing of Discrete Distributions under Rare/Weak Perturbations","display_name":"Two-sample Testing of Discrete Distributions under Rare/Weak Perturbations","publication_year":2021,"publication_date":"2021-07-12","ids":{"openalex":"https://openalex.org/W3198699721","doi":"https://doi.org/10.1109/isit45174.2021.9517991","mag":"3198699721"},"language":"en","primary_location":{"id":"doi:10.1109/isit45174.2021.9517991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit45174.2021.9517991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5074838733","display_name":"Alon Kipnis","orcid":"https://orcid.org/0000-0003-3798-8035"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alon Kipnis","raw_affiliation_strings":["Stanford University,Department of Statistics","Department of Statistics, Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Statistics","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Statistics, Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065355421","display_name":"David L. Donoho","orcid":"https://orcid.org/0000-0003-1830-710X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David. L. Donoho","raw_affiliation_strings":["Stanford University,Department of Statistics","Department of Statistics, Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Statistics","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Statistics, Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5074838733"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.42,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69665761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3314","last_page":"3319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9922999739646912,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9922999739646912,"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/T10968","display_name":"Statistical Distribution Estimation and Applications","score":0.9707000255584717,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11235","display_name":"Statistical Methods in Clinical Trials","score":0.9642000198364258,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.7216200232505798},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.5603001117706299},{"id":"https://openalex.org/keywords/null-model","display_name":"Null model","score":0.5596268773078918},{"id":"https://openalex.org/keywords/binomial-distribution","display_name":"Binomial distribution","score":0.49566662311553955},{"id":"https://openalex.org/keywords/negative-binomial-distribution","display_name":"Negative binomial distribution","score":0.48045557737350464},{"id":"https://openalex.org/keywords/null","display_name":"Null (SQL)","score":0.4771665632724762},{"id":"https://openalex.org/keywords/diagram","display_name":"Diagram","score":0.47388049960136414},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47241392731666565},{"id":"https://openalex.org/keywords/null-hypothesis","display_name":"Null hypothesis","score":0.46685367822647095},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.43390464782714844},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.43183383345603943},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4272732734680176},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.39496734738349915},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.17537057399749756},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.14851197600364685},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.10180041193962097}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.7216200232505798},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5603001117706299},{"id":"https://openalex.org/C36382193","wikidata":"https://www.wikidata.org/wiki/Q7068966","display_name":"Null model","level":2,"score":0.5596268773078918},{"id":"https://openalex.org/C41054675","wikidata":"https://www.wikidata.org/wiki/Q185547","display_name":"Binomial distribution","level":2,"score":0.49566662311553955},{"id":"https://openalex.org/C199335787","wikidata":"https://www.wikidata.org/wiki/Q743364","display_name":"Negative binomial distribution","level":3,"score":0.48045557737350464},{"id":"https://openalex.org/C203763787","wikidata":"https://www.wikidata.org/wiki/Q371029","display_name":"Null (SQL)","level":2,"score":0.4771665632724762},{"id":"https://openalex.org/C186399060","wikidata":"https://www.wikidata.org/wiki/Q959962","display_name":"Diagram","level":2,"score":0.47388049960136414},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47241392731666565},{"id":"https://openalex.org/C191988596","wikidata":"https://www.wikidata.org/wiki/Q628374","display_name":"Null hypothesis","level":2,"score":0.46685367822647095},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.43390464782714844},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.43183383345603943},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4272732734680176},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.39496734738349915},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.17537057399749756},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.14851197600364685},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.10180041193962097},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit45174.2021.9517991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit45174.2021.9517991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W143242907","https://openalex.org/W1516900628","https://openalex.org/W1532325895","https://openalex.org/W1536084649","https://openalex.org/W1696066093","https://openalex.org/W1752770703","https://openalex.org/W1930690627","https://openalex.org/W1981106668","https://openalex.org/W2014100575","https://openalex.org/W2028072731","https://openalex.org/W2031648200","https://openalex.org/W2064921494","https://openalex.org/W2068728923","https://openalex.org/W2074673068","https://openalex.org/W2076333420","https://openalex.org/W2081985429","https://openalex.org/W2097492546","https://openalex.org/W2103244186","https://openalex.org/W2133264613","https://openalex.org/W2138256420","https://openalex.org/W2140107833","https://openalex.org/W2171086879","https://openalex.org/W2182991033","https://openalex.org/W2407691716","https://openalex.org/W2419099043","https://openalex.org/W2912780347","https://openalex.org/W2950830772","https://openalex.org/W2952058015","https://openalex.org/W2954249017","https://openalex.org/W2962841567","https://openalex.org/W2963064614","https://openalex.org/W2963153079","https://openalex.org/W3099946720","https://openalex.org/W3102033309","https://openalex.org/W3106247953","https://openalex.org/W3168192763","https://openalex.org/W4206031910","https://openalex.org/W4206202898","https://openalex.org/W4243957593","https://openalex.org/W4252283476","https://openalex.org/W4302376672","https://openalex.org/W6631834165","https://openalex.org/W6640144727","https://openalex.org/W6685267954","https://openalex.org/W6685779351"],"related_works":["https://openalex.org/W2037403216","https://openalex.org/W1602555103","https://openalex.org/W120285656","https://openalex.org/W2887966696","https://openalex.org/W2052110748","https://openalex.org/W4244236455","https://openalex.org/W62389518","https://openalex.org/W2505382103","https://openalex.org/W2802215909","https://openalex.org/W2736742737"],"abstract_inverted_index":{"We":[0,103],"propose":[1],"a":[2,24,36,105,143,179],"method":[3,73,157],"to":[4,57],"perform":[5,104],"two-sample":[6],"tests":[7],"on":[8,35,48],"discrete":[9],"distributions,":[10],"i.e.,":[11],"an":[12,59,133],"unsupervised":[13,61],"discriminator":[14,63],"testing":[15],"whether":[16],"two":[17,85],"frequency":[18],"tables":[19],"were":[20],"each":[21],"sampled":[22],"from":[23],"single":[25],"unspecified":[26],"probability":[27],"distribution.":[28],"Our":[29],"proposal":[30,125],"takes":[31],"feature-by-feature":[32],"P-values":[33,43],"based":[34],"binomial":[37,69],"allocation":[38,70],"model,":[39],"and":[40,97,117],"combines":[41],"the":[42,68,79,111,149,156,159,164,173,189,197,203,206],"using":[44],"Higher":[45],"Criticism.":[46],"Performance":[47],"real-world":[49],"data":[50],"(e.g.":[51],"authorship":[52],"attribution":[53],"challenges)":[54],"shows":[55],"this":[56],"be":[58],"effective":[60],"untrained":[62],"even":[64],"in":[65,78,93,109,148,163],"violations":[66],"of":[67,132,142,175,205],"model.":[71],"The":[72],"has":[74],"interesting":[75],"theoretical":[76],"properties,":[77],"\u2018rare/weak":[80],"departures\u2019":[81],"setting":[82],"where,":[83],"if":[84],"distributions":[86],"are":[87,154,193],"actually":[88],"different,":[89],"they":[90],"differ":[91],"only":[92,98],"relatively":[94,100],"few":[95],"features":[96],"by":[99],"subtle":[101],"amounts.":[102],"phase":[106,112,161,176,198],"diagram":[107,162,199,208],"analysis":[108],"which":[110],"space":[113,177],"quantifies":[114],"how":[115,118],"rare":[116],"weak":[119],"such":[120],"departures":[121],"are.":[122],"Although":[123],"our":[124],"does":[126,137],"not":[127,210],"require":[128,139],"any":[129,140],"formal":[130],"specification":[131,141],"alternative":[134],"hypothesis,":[135,147],"nor":[136],"it":[138,167],"baseline":[144],"or":[145],"null":[146],"limit":[150,190],"where":[151,178,191],"word":[152],"counts":[153,192],"high,":[155],"delivers":[158],"optimal":[160],"rare/weak":[165],"setting:":[166],"is":[168,209],"asymptotically":[169],"fully":[170,186],"powerful":[171],"inside":[172],"region":[174],"formally":[180],"specified":[181],"test":[182],"would":[183],"have":[184],"been":[185],"powerful.":[187],"In":[188],"low,":[194],"we":[195],"derive":[196],"as":[200],"well,":[201],"although":[202],"optimality":[204],"resulting":[207],"discussed":[211],"here.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}