{"id":"https://openalex.org/W7128635023","doi":"https://doi.org/10.1109/focs63196.2025.00045","title":"Embeddings into Similarity Measures for Nearest Neighbor Search","display_name":"Embeddings into Similarity Measures for Nearest Neighbor Search","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7128635023","doi":"https://doi.org/10.1109/focs63196.2025.00045"},"language":null,"primary_location":{"id":"doi:10.1109/focs63196.2025.00045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/focs63196.2025.00045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 66th Annual Symposium on Foundations of Computer Science (FOCS)","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/A5088346829","display_name":"Alexandr Andoni","orcid":"https://orcid.org/0009-0004-8042-0976"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandr Andoni","raw_affiliation_strings":["Columbia University,NYC,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,NYC,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091285415","display_name":"Negev Shekel Nosatzki","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Negev Shekel Nosatzki","raw_affiliation_strings":["Columbia University,NYC,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,NYC,USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64148942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"864","last_page":"893"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.17409999668598175,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.17409999668598175,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.1655000001192093,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.08190000057220459,"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/jaccard-index","display_name":"Jaccard index","score":0.7246000170707703},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6754000186920166},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.671999990940094},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.640500009059906},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6100999712944031},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.5965999960899353},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5777999758720398},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5144000053405762}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.7246000170707703},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6754000186920166},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.671999990940094},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6657999753952026},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.640500009059906},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6100999712944031},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5965999960899353},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5777999758720398},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5144000053405762},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.4584999978542328},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3862999975681305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3732999861240387},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C182964748","wikidata":"https://www.wikidata.org/wiki/Q208216","display_name":"Triangle inequality","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C53661774","wikidata":"https://www.wikidata.org/wiki/Q13108095","display_name":"Cover tree","level":5,"score":0.298799991607666},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2930000126361847},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2883000075817108},{"id":"https://openalex.org/C161986146","wikidata":"https://www.wikidata.org/wiki/Q4896845","display_name":"Best bin first","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.2628999948501587}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/focs63196.2025.00045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/focs63196.2025.00045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 66th Annual Symposium on Foundations of Computer Science (FOCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4007892906665802,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,19,57],"introduce":[1],"the":[2,15,41,92],"notion":[3],"of":[4,30,47,132],"metric":[5,31],"embeddings":[6,22,60],"into":[7,23,49],"a":[8,28,62,77],"similarity":[9,25],"measure":[10],"over":[11,108,117],"$\\mathbb{R}_{+}^{m}$,":[12],"such":[13,24,73],"as":[14],"weighted":[16],"Jaccard":[17],"coefficient.":[18],"develop":[20],"average":[21],"measures":[26],"for":[27,65,89,119],"number":[29],"spaces,":[32],"with":[33,61],"(appropriately":[34],"defined)":[35],"distortion":[36,46],"that":[37,71],"is":[38],"smaller":[39],"than":[40],"best":[42],"possible":[43],"or":[44,51,55],"known":[45],"embedding":[48,75],"$\\ell_{1}$":[50],"$\\ell_{2}$":[52],"spaces":[53],"(biLipschitz":[54],"average).":[56],"complement":[58],"our":[59],"new":[63,86],"algorithm":[64],"Approximate":[66],"Nearest":[67],"Neighbor":[68],"Search":[69],"(ANNS)":[70],"leverages":[72],"an":[74,98],"in":[76,129],"black":[78],"box":[79],"fashion.":[80],"Combining":[81],"these":[82],"results,":[83],"we":[84],"obtain":[85],"efficient":[87],"algorithms":[88],"ANNS":[90],"under":[91],"following":[93],"two":[94],"classic":[95],"metrics,":[96],"achieving":[97],"exponential":[99],"improvement":[100],"to":[101,125],"longstanding":[102],"prior":[103],"work:":[104],"-":[105,115],"Edit":[106],"distance":[107],"length-":[109],"k":[110],"strings:":[111],"$\\operatorname{poly}(\\log":[112],"k)$":[113],"approximation;":[114],"$\\ell_{p}$":[116],"$\\mathbb{R}^{d}$,":[118],"$p\\gt2:":[120],"O(\\log":[121],"p)$":[122],"approximation":[123],"(known":[124],"be":[126],"asymptotically":[127],"optimal":[128],"relevant":[130],"models":[131],"computation).":[133]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-12T00:00:00"}