{"id":"https://openalex.org/W2006120644","doi":"https://doi.org/10.1109/mlsp.2015.7324319","title":"A rate-distortion framework for supervised learning","display_name":"A rate-distortion framework for supervised learning","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2006120644","doi":"https://doi.org/10.1109/mlsp.2015.7324319","mag":"2006120644"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2015.7324319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2015.7324319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5068254472","display_name":"Matthew Nokleby","orcid":"https://orcid.org/0000-0002-3454-4212"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matthew Nokleby","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","Dept. of Electrical and Computer Engineering, Duke University, Durham, NC 27708, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Duke University, Durham, NC 27708, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008645615","display_name":"Ahmad Beirami","orcid":"https://orcid.org/0000-0002-1998-5271"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmad Beirami","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","Dept. of Electrical and Computer Engineering, Duke University, Durham, NC 27708, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Duke University, Durham, NC 27708, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037795370","display_name":"Robert Calderbank","orcid":"https://orcid.org/0000-0003-2084-9717"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Calderbank","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","Dept. of Electrical and Computer Engineering, Duke University, Durham, NC 27708, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Duke University, Durham, NC 27708, USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068254472"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.04199447,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"19","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9991000294685364,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9991000294685364,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9976999759674072,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9945999979972839,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.727745532989502},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5941697955131531},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5738738775253296},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5509754419326782},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5466835498809814},{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.5465043783187866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5163475275039673},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5094366669654846},{"id":"https://openalex.org/keywords/distortion-function","display_name":"Distortion function","score":0.49192094802856445},{"id":"https://openalex.org/keywords/rate\u2013distortion-theory","display_name":"Rate\u2013distortion theory","score":0.4888586401939392},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4868568778038025},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.462326318025589},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.45106273889541626},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43525418639183044},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4219316244125366},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3859488070011139},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.33312514424324036},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.24172759056091309}],"concepts":[{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.727745532989502},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5941697955131531},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5738738775253296},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5509754419326782},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5466835498809814},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.5465043783187866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5163475275039673},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5094366669654846},{"id":"https://openalex.org/C2780803321","wikidata":"https://www.wikidata.org/wiki/Q5283073","display_name":"Distortion function","level":3,"score":0.49192094802856445},{"id":"https://openalex.org/C64185310","wikidata":"https://www.wikidata.org/wiki/Q843483","display_name":"Rate\u2013distortion theory","level":3,"score":0.4888586401939392},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4868568778038025},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.462326318025589},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.45106273889541626},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43525418639183044},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4219316244125366},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3859488070011139},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.33312514424324036},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24172759056091309},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp.2015.7324319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2015.7324319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W195150910","https://openalex.org/W1516508599","https://openalex.org/W1978923178","https://openalex.org/W2029538739","https://openalex.org/W2038390905","https://openalex.org/W2090559885","https://openalex.org/W2100180150","https://openalex.org/W2106491486","https://openalex.org/W2108995755","https://openalex.org/W2110798204","https://openalex.org/W2136922672","https://openalex.org/W2148861585","https://openalex.org/W2149298154","https://openalex.org/W2156909104","https://openalex.org/W2160570986","https://openalex.org/W2167507722","https://openalex.org/W2478708596","https://openalex.org/W2911964244","https://openalex.org/W4230674625","https://openalex.org/W4238284510","https://openalex.org/W4240914861","https://openalex.org/W4243392806","https://openalex.org/W6676481782"],"related_works":["https://openalex.org/W1594577932","https://openalex.org/W4386555803","https://openalex.org/W2588738813","https://openalex.org/W1999453492","https://openalex.org/W1413489299","https://openalex.org/W2964332837","https://openalex.org/W4289655361","https://openalex.org/W2767580541","https://openalex.org/W2169872009","https://openalex.org/W2059965583"],"abstract_inverted_index":{"An":[0],"information-theoretic":[1],"framework":[2,21],"is":[3,22,132],"presented":[4],"for":[5,12,139,146],"bounding":[6],"the":[7,34,45,58,75,81,86,98,103,118,135,147],"number":[8,111],"of":[9,37,57,71,85,102,112,129,137],"samples":[10,114],"needed":[11,115],"supervised":[13],"learning":[14],"in":[15,33,100],"a":[16,41,47,54,68,109,124],"parametric":[17,42],"Bayesian":[18,43],"setting.":[19],"This":[20],"inspired":[23],"by":[24],"an":[25],"analogy":[26],"with":[27],"rate-distortion":[28],"theory,":[29],"which":[30,140],"characterizes":[31],"tradeoffs":[32],"lossy":[35],"compression":[36],"random":[38,55],"sources.":[39],"In":[40],"environment,":[44],"maximum":[46],"posteriori":[48],"classifier":[49,83,88],"can":[50,64,89,142],"be":[51,65,90],"viewed":[52,66,91],"as":[53,67,92],"function":[56],"model":[59],"parameters.":[60],"Labeled":[61],"training":[62,113],"data":[63],"finite-rate":[69],"encoding":[70],"that":[72],"source,":[73],"and":[74],"excess":[76],"loss":[77],"due":[78],"to":[79,116,122],"using":[80],"learned":[82],"instead":[84],"MAP":[87],"distortion.":[93],"A":[94],"strict":[95],"bound":[96,131],"on":[97,134],"loss-measured":[99],"terms":[101],"expected":[104,119],"total":[105,120],"variation-is":[106],"derived,":[107],"providing":[108],"minimum":[110],"drive":[117],"variation":[121],"within":[123],"specified":[125],"tolerance.":[126],"The":[127],"tightness":[128],"this":[130],"demonstrated":[133],"classification":[136],"Gaus-sians,":[138],"one":[141],"derive":[143],"closed-form":[144],"expressions":[145],"bound.":[148]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}