{"id":"https://openalex.org/W4407462795","doi":"https://doi.org/10.1109/tit.2025.3541375","title":"On <i>k</i>-Mer-Based and Maximum Likelihood Estimation Algorithms for Trace Reconstruction","display_name":"On <i>k</i>-Mer-Based and Maximum Likelihood Estimation Algorithms for Trace Reconstruction","publication_year":2025,"publication_date":"2025-02-13","ids":{"openalex":"https://openalex.org/W4407462795","doi":"https://doi.org/10.1109/tit.2025.3541375"},"language":"en","primary_location":{"id":"doi:10.1109/tit.2025.3541375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2025.3541375","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"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 Transactions on 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/A5014279694","display_name":"Kuan Cheng","orcid":"https://orcid.org/0000-0002-8972-1749"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210161752","display_name":"Beijing Haidian Hospital","ror":"https://ror.org/058x5eq06","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210161752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kuan Cheng","raw_affiliation_strings":["School of Computer Science, Peking University, Haidian, Beijing, China","Peking University, Haidian, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8972-1749","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Haidian, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Haidian, Beijing, China","institution_ids":["https://openalex.org/I4210161752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090091569","display_name":"Elena Grigorescu","orcid":"https://orcid.org/0000-0001-9673-4313"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Elena Grigorescu","raw_affiliation_strings":["Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, Canada","University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0001-9673-4313","affiliations":[{"raw_affiliation_string":"Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353984","display_name":"Xin Li","orcid":"https://orcid.org/0000-0002-9408-2451"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA","Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-9408-2451","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101519422","display_name":"Madhu Sudan","orcid":"https://orcid.org/0000-0003-3718-6489"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Madhu Sudan","raw_affiliation_strings":["School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","Harvard University, Cambridge, Massachusetts, USA"],"raw_orcid":"https://orcid.org/0000-0003-3718-6489","affiliations":[{"raw_affiliation_string":"School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Harvard University, Cambridge, Massachusetts, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085562284","display_name":"Minshen Zhu","orcid":"https://orcid.org/0000-0003-1927-6085"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minshen Zhu","raw_affiliation_strings":["Department of Computer Science, Purdue University, West Lafayette, IN, USA","Purdue University, USA"],"raw_orcid":"https://orcid.org/0000-0003-1927-6085","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Purdue University, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8048,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.89324606,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"71","issue":"4","first_page":"2591","last_page":"2603"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.951200008392334,"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"}},"topics":[{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.951200008392334,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9362999796867371,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6517502069473267},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.6032634973526001},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.5594205260276794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5120165944099426},{"id":"https://openalex.org/keywords/maximum-likelihood-sequence-estimation","display_name":"Maximum likelihood sequence estimation","score":0.47299250960350037},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.39071694016456604},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3668096661567688},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.23084086179733276}],"concepts":[{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6517502069473267},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.6032634973526001},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.5594205260276794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5120165944099426},{"id":"https://openalex.org/C191462741","wikidata":"https://www.wikidata.org/wiki/Q6795902","display_name":"Maximum likelihood sequence estimation","level":3,"score":0.47299250960350037},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.39071694016456604},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3668096661567688},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.23084086179733276},{"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/tit.2025.3541375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2025.3541375","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"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 Transactions on Information Theory","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6279317373","display_name":null,"funder_award_id":"62472008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1133414672","https://openalex.org/W1967505984","https://openalex.org/W1969151232","https://openalex.org/W1995897489","https://openalex.org/W2005245976","https://openalex.org/W2031816626","https://openalex.org/W2058068142","https://openalex.org/W2081933490","https://openalex.org/W2170484108","https://openalex.org/W2564763601","https://openalex.org/W2584062640","https://openalex.org/W2911475043","https://openalex.org/W2912739023","https://openalex.org/W2951269465","https://openalex.org/W2963134372","https://openalex.org/W2963670229","https://openalex.org/W2964199960","https://openalex.org/W2969308577","https://openalex.org/W2971926581","https://openalex.org/W2979059622","https://openalex.org/W3028579427","https://openalex.org/W3033084890","https://openalex.org/W3097193862","https://openalex.org/W3117245243","https://openalex.org/W3128220280","https://openalex.org/W3161798670","https://openalex.org/W3169706614","https://openalex.org/W3197288570","https://openalex.org/W3197318729","https://openalex.org/W3198708829","https://openalex.org/W4226090901","https://openalex.org/W4400021110","https://openalex.org/W6656576250","https://openalex.org/W6665204704","https://openalex.org/W6666485203","https://openalex.org/W6674695496","https://openalex.org/W6747734592","https://openalex.org/W6782677995","https://openalex.org/W6798252878","https://openalex.org/W6798357154","https://openalex.org/W6798960783","https://openalex.org/W6841087898","https://openalex.org/W6873089463"],"related_works":["https://openalex.org/W1499442185","https://openalex.org/W2366184732","https://openalex.org/W2379466508","https://openalex.org/W2120595071","https://openalex.org/W3139607207","https://openalex.org/W2090147078","https://openalex.org/W1600683375","https://openalex.org/W2155160077","https://openalex.org/W2978085921","https://openalex.org/W2353424004"],"abstract_inverted_index":{"The":[0,299],"goal":[1],"of":[2,26,40,59,94,104,117,124,145,229,249,256,294,297,301,341,352,359,370,388,391,408,418,451,458,465,477],"the":[3,87,91,107,115,136,156,230,241,244,250,292,307,328,350,383,389,416,419,427,432,437,443,463],"trace":[4,32,95,108,251,274,353],"reconstruction":[5,109,252,275],"problem":[6,253],"is":[7,33,86,120,315,334],"to":[8,216,326,376,401,435,455],"recover":[9],"a":[10,31,34,405,447,456],"string":[11,158,429],"<inline-formula":[12,49,75,163,189,198,278],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[13,24,28,42,50,66,76,127,138,147,153,160,164,181,190,199,219,225,232,270,279,460,479],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[14,51,77,165,191,200,280],"<tex-math":[15,52,78,166,192,201,281],"notation=\"LaTeX\">$\\mathbf":[16],"{x}\\in":[17],"\\{0,1\\}^{n}$":[18],"</tex-math></inline-formula>":[19,83,195,210,288],"given":[20,47,227],"many":[21],"independent":[22],"<italic":[23,146,152,180,218,231,269,459,478],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">traces</i>":[25],"<bold":[27,41,65,159,224],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">x</b>,":[29,161],"where":[30],"subsequence":[35],"obtained":[36,133],"from":[37,74,197],"deleting":[38],"bits":[39],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">x</b>":[43,67,226],"independently":[44],"with":[45],"some":[46],"probability":[48],"notation=\"LaTeX\">$p\\in":[53],"[0,1$":[54],"</tex-math></inline-formula>).":[55],"A":[56],"recent":[57],"result":[58,89,265,303,333,414],"Chase":[60,312],"(STOC":[61,313],"2021)":[62,314],"shows":[63,266,305],"how":[64],"can":[68,130,185],"be":[69,132,186,217,483],"determined":[70],"(in":[71],"exponential":[72],"time)":[73],"notation=\"LaTeX\">$\\exp":[79,282],"({O}(n^{1/5})\\log":[80],"^{5}":[81],"n)$":[82],"traces.":[84,211,298],"This":[85,332],"state-of-the-art":[88],"on":[90,122,379,403],"sample":[92],"complexity":[93],"reconstruction.":[96],"In":[97],"this":[98,295,302,475],"paper":[99],"we":[100,254],"consider":[101],"two":[102,369],"kinds":[103],"algorithms":[105,237],"for":[106,162,273,468],"problem.":[110],"We":[111,212,440],"first":[112],"observe":[113],"that":[114,176,267,306,344,368,398,430,442,474],"bound":[116],"Chase,":[118],"which":[119,424],"based":[121],"statistics":[123,142,178],"arbitrary":[125],"length-<italic":[126],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">k</i>":[128],"subsequences,":[129],"also":[131,304],"by":[134,311,336],"considering":[135,337],"\u201c<italic":[137],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">k</i>-mer":[139,182,233],"statistics\u201d,":[140],"i.e.,":[141,453],"regarding":[143],"occurrences":[144],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">contiguous":[148],"k</i>-bit":[149],"strings":[150],"(a.k.a,":[151],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">k-mers</i>)":[154],"in":[155,243,324,349,382,462],"initial":[157],"notation=\"LaTeX\">$k":[167],"=":[168],"2n^{1/5}$":[169],"</tex-math></inline-formula>.":[170],"Mazooji":[171],"and":[172,246,261,318,366,472],"Shomorony":[173],"(arXiv.2210.10917)":[174],"show":[175,441,473],"such":[177,392],"(called":[179],"density":[183,234],"map)":[184],"estimated":[187],"within":[188],"notation=\"LaTeX\">$\\varepsilon":[193],"$":[194],"accuracy":[196],"notation=\"LaTeX\">$":[202],"{\\mathrm":[203],"{poly}}":[204],"(n,":[205],"2^{k},":[206],"1/":[207],"{\\varepsilon":[208],"})$":[209],"call":[213],"an":[214,338,380,469],"algorithm":[215,272,445],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">k-mer-based</i>":[220],"if":[221],"it":[222],"reconstructs":[223],"estimates":[228],"map.":[235],"Such":[236],"essentially":[238,316],"capture":[239],"all":[240],"analyses":[242],"worst-case":[245,329],"smoothed-complexity":[247],"models":[248],"know":[255],"so":[257],"far.":[258],"Our":[259,386,411],"first,":[260],"technically":[262],"more":[263],"involved,":[264],"any":[268],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">k</i>-mer-based":[271],"must":[276],"use":[277],"(\\Omega":[283],"(n^{1/5}":[284],"\\sqrt":[285],"{\\log":[286],"n}))$":[287],"traces,":[289,452],"thus":[290],"establishing":[291],"optimality":[293],"number":[296,450,464],"analysis":[300,308],"technique":[309],"used":[310],"tight,":[317],"hence":[319],"new":[320,395],"techniques":[321],"are":[322,373],"needed":[323,467],"order":[325],"improve":[327],"upper":[330],"bound.":[331],"shown":[335],"appropriate":[339],"class":[340],"real":[342],"polynomials,":[343],"have":[345],"been":[346],"previously":[347],"studied":[348],"context":[351],"estimation":[354],"(De,":[355],"O\u2019Donnell,":[356],"Servedio.":[357],"Annals":[358],"Probability":[360],"2019;":[361],"Nazarov,":[362],"Peres.":[363],"STOC":[364],"2017),":[365],"proving":[367],"these":[371,409],"polynomials":[372,393],"very":[374],"close":[375],"each":[377],"other":[378],"arc":[381],"complex":[384],"plane.":[385],"proof":[387],"proximity":[390],"uses":[394,446],"technical":[396],"ingredients":[397],"allow":[399],"us":[400],"focus":[402],"just":[404],"few":[406],"coefficients":[407],"polynomials.":[410],"second,":[412],"simple,":[413],"considers":[415],"performance":[417],"Maximum":[420],"Likelihood":[421],"Estimator":[422],"(MLE),":[423],"specifically":[425],"picks":[426],"source":[428],"has":[431],"maximum":[433],"likelihood":[434],"generate":[436],"samples":[438,466],"(traces).":[439],"MLE":[444],"nearly":[448],"optimal":[449,470],"up":[454],"factor":[457,476],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">n</i>":[461,480],"algorithm,":[471],"loss":[481],"may":[482],"necessary":[484],"under":[485],"general":[486],"\u201cmodel":[487],"estimation\u201d":[488],"settings.":[489]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-02-14T00:00:00"}