{"id":"https://openalex.org/W4402475917","doi":"https://doi.org/10.1371/journal.pcbi.1012427","title":"Calibrating dimension reduction hyperparameters in the presence of noise","display_name":"Calibrating dimension reduction hyperparameters in the presence of noise","publication_year":2024,"publication_date":"2024-09-12","ids":{"openalex":"https://openalex.org/W4402475917","doi":"https://doi.org/10.1371/journal.pcbi.1012427","pmid":"https://pubmed.ncbi.nlm.nih.gov/39264943"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1012427","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1012427","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1371/journal.pcbi.1012427","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088813995","display_name":"Justin Lin","orcid":"https://orcid.org/0009-0007-7190-2430"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Justin Lin","raw_affiliation_strings":["Department of Mathematics, Indiana University, Bloomington, Indiana, United States of America"],"raw_orcid":"https://orcid.org/0009-0007-7190-2430","affiliations":[{"raw_affiliation_string":"Department of Mathematics, Indiana University, Bloomington, Indiana, United States of America","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050341558","display_name":"Julia Fukuyama","orcid":"https://orcid.org/0000-0002-7590-5563"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julia Fukuyama","raw_affiliation_strings":["Department of Statistics, Indiana University, Bloomington, Indiana, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Indiana University, Bloomington, Indiana, United States of America","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5088813995"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":0.9546,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73622642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"20","issue":"9","first_page":"e1012427","last_page":"e1012427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.988099992275238,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9746000170707703,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.9293223023414612},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.7710483074188232},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.7603565454483032},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7474465370178223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5314475893974304},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49657994508743286},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4940960705280304},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4496694505214691},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44867372512817383},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.44420239329338074},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.428560346364975},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4228339195251465},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37547367811203003},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.17528164386749268},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15504074096679688}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9293223023414612},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.7710483074188232},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7603565454483032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7474465370178223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5314475893974304},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49657994508743286},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4940960705280304},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4496694505214691},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44867372512817383},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.44420239329338074},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.428560346364975},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4228339195251465},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37547367811203003},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.17528164386749268},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15504074096679688},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002138","descriptor_name":"Calibration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002138","descriptor_name":"Calibration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002138","descriptor_name":"Calibration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002138","descriptor_name":"Calibration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002138","descriptor_name":"Calibration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059629","descriptor_name":"Signal-To-Noise Ratio","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059629","descriptor_name":"Signal-To-Noise Ratio","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059629","descriptor_name":"Signal-To-Noise Ratio","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059629","descriptor_name":"Signal-To-Noise Ratio","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059629","descriptor_name":"Signal-To-Noise Ratio","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1371/journal.pcbi.1012427","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1012427","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:39264943","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39264943","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS computational biology","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11421778","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11421778","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11421778/pdf/pcbi.1012427.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Comput Biol","raw_type":"Text"},{"id":"pmh:oai:RePEc:plo:pcbi00:1012427","is_oa":false,"landing_page_url":"https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1012427","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1012427","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1012427","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1801065823","https://openalex.org/W1982729887","https://openalex.org/W1997780235","https://openalex.org/W2032230795","https://openalex.org/W2088477804","https://openalex.org/W2113637789","https://openalex.org/W2148541040","https://openalex.org/W2187089797","https://openalex.org/W2542768043","https://openalex.org/W2902652978","https://openalex.org/W2951638683","https://openalex.org/W2975605169","https://openalex.org/W2989747508","https://openalex.org/W2993894543","https://openalex.org/W3111307227","https://openalex.org/W3127452014","https://openalex.org/W4205921232","https://openalex.org/W4285794641","https://openalex.org/W4385945347"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4298369531","https://openalex.org/W3155135229","https://openalex.org/W3211783303"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,12,22,57,85,104,120,134,202],"dimension":[3,52,81,91],"reduction":[4,92],"tools":[5,16],"is":[6,36,41,48],"to":[7,30,70,98,116,147,154,196],"construct":[8],"a":[9,20,37,102,142,191],"low-dimensional":[10],"representation":[11],"high-dimensional":[13],"data.":[14],"These":[15,111],"are":[17,68,75,113,181],"employed":[18,69],"for":[19,177],"variety":[21],"reasons":[23],"such":[24,62,76],"as":[25,63,101],"noise":[26,107,136],"reduction,":[27],"visualization,":[28],"and":[29,66,95,106,140,168,179,184],"lower":[31],"computational":[32],"costs.":[33],"However,":[34],"there":[35],"fundamental":[38],"issue":[39],"that":[40,47,144],"discussed":[42],"in":[43,51,161,199],"other":[44,58],"modeling":[45,59],"problems":[46],"often":[49],"overlooked":[50],"reduction-overfitting.":[53],"In":[54,127],"the":[55,86,118,121,125,132,156,163,186,200],"context":[56],"problems,":[60],"techniques":[61],"feature-selection,":[64],"cross-validation,":[65],"regularization":[67],"combat":[71],"overfitting,":[72],"but":[73],"rarely":[74],"precautions":[77],"taken":[78],"when":[79,108,137,165],"applying":[80,166],"reduction.":[82],"Prior":[83],"applications":[84],"two":[87],"most":[88],"popular":[89],"non-linear":[90],"methods,":[93],"t-SNE":[94,167],"UMAP,":[96],"fail":[97],"acknowledge":[99],"data":[100,164],"combination":[103],"signal":[105],"assessing":[109],"performance.":[110],"methods":[112],"typically":[114],"calibrated":[115],"capture":[117],"entirety":[119],"data,":[122],"not":[123],"just":[124],"signal.":[126],"this":[128,152],"paper,":[129],"we":[130,172],"demonstrate":[131],"importance":[133],"acknowledging":[135],"calibrating":[138],"hyperparameters":[139,198],"present":[141],"framework":[143,153],"enables":[145],"users":[146],"do":[148],"so.":[149],"We":[150,188],"use":[151,195],"explore":[155],"role":[157],"hyperparameter":[158],"calibration":[159],"plays":[160],"overfitting":[162],"UMAP.":[169],"More":[170],"specifically,":[171],"show":[173],"previously":[174],"recommended":[175],"values":[176],"perplexity":[178],"n_neighbors":[180],"too":[182],"small":[183],"overfit":[185],"noise.":[187,203],"also":[189],"provide":[190],"workflow":[192],"others":[193],"may":[194],"calibrate":[197],"presence":[201]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-10T07:06:39.071514","created_date":"2025-10-10T00:00:00"}