{"id":"https://openalex.org/W7204187224","doi":"https://doi.org/10.1109/isit62367.2026.11654044","title":"Excess Description Length: An Information Measure for Generalizable Structure Learned from Finite Data","display_name":"Excess Description Length: An Information Measure for Generalizable Structure Learned from Finite Data","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7204187224","doi":"https://doi.org/10.1109/isit62367.2026.11654044"},"language":"en","primary_location":{"id":"doi:10.1109/isit62367.2026.11654044","doi":"https://doi.org/10.1109/isit62367.2026.11654044","is_oa":true,"landing_page_url":"https://doi.org/10.1109/isit62367.2026.11654044","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"IEEE International Symposium on Information Theory (ISIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/isit62367.2026.11654044","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119937068","display_name":"Elizabeth Donoway","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Elizabeth Donoway","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5119937068"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71843707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.701200008392334,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.701200008392334,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.051600001752376556,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.031099999323487282,"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/information-theoretic-measures","display_name":"information measures","score":0.7689999938011169},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.6779999732971191},{"id":"https://openalex.org/keywords/structure-learning","display_name":"structure learning","score":0.6779999732971191},{"id":"https://openalex.org/keywords/finite-data","display_name":"finite data","score":0.8899999856948853},{"id":"https://openalex.org/keywords/model-complexity","display_name":"model complexity","score":0.574999988079071}],"concepts":[{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.6086999773979187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5533000230789185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4790000021457672},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3278999924659729},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31130000948905945},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3086000084877014},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29649999737739563},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29089999198913574},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit62367.2026.11654044","doi":"https://doi.org/10.1109/isit62367.2026.11654044","is_oa":true,"landing_page_url":"https://doi.org/10.1109/isit62367.2026.11654044","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"IEEE International Symposium on Information Theory (ISIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1109/isit62367.2026.11654044","doi":"https://doi.org/10.1109/isit62367.2026.11654044","is_oa":true,"landing_page_url":"https://doi.org/10.1109/isit62367.2026.11654044","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"IEEE International Symposium on Information Theory (ISIT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1570963478","https://openalex.org/W1995875735","https://openalex.org/W2054658115","https://openalex.org/W2132119275","https://openalex.org/W2478708596","https://openalex.org/W2796293253"],"related_works":["https://openalex.org/W7133256343","https://openalex.org/W7197028418","https://openalex.org/W7128127027","https://openalex.org/W2312294163","https://openalex.org/W3019713249","https://openalex.org/W2328230987","https://openalex.org/W3168107900","https://openalex.org/W96853880","https://openalex.org/W2600467563","https://openalex.org/W6931651463"],"abstract_inverted_index":{"Learning":[0],"algorithms":[1],"transfer":[2,164],"predictive":[3],"structure":[4],"from":[5,41,151],"data":[6,62,114],"into":[7],"model":[8],"parameters,":[9],"yet":[10],"existing":[11],"information-theoretic":[12],"quantities":[13],"primarily":[14],"characterize":[15],"either":[16],"dataset":[17],"complexity":[18],"or":[19],"asymptotic":[20],"learning":[21,39,150,166],"costs.":[22],"We":[23,84,138],"introduce":[24],"excess":[25,55],"description":[26],"length":[27],"(EDL),":[28],"a":[29,38,65,103,158],"compute-indexed":[30],"measure":[31],"of":[32,91,113],"the":[33,54,71,81,111,136,145],"generalizable":[34,131],"information":[35,93,132,163],"extracted":[36],"by":[37],"algorithm":[40],"finite":[42,170],"data.":[43,137],"EDL":[44,87,141,156],"admits":[45],"an":[46,92],"operational":[47],"interpretation":[48],"via":[49],"prequential":[50],"coding:":[51],"it":[52],"is":[53],"codelength":[56],"incurred":[57],"on":[58,80,106,169],"first":[59],"exposure":[60],"to":[61,64],"relative":[63],"predictor":[66],"whose":[67],"expected":[68],"log-loss":[69],"equals":[70],"final":[72],"model\u2019s":[73],"population":[74],"loss,":[75],"thereby":[76],"excluding":[77],"memorization":[78],"effects":[79],"training":[82],"set.":[83],"establish":[85,155],"that":[86,126,140],"satisfies":[88],"fundamental":[89],"properties":[90],"measure\u2014non-negativity,":[94],"additivity":[95],"under":[96],"product":[97],"structure,":[98],"monotonicity":[99],"in":[100,135,165],"compute,":[101],"and":[102,117],"processing":[104],"bound":[105,124],"extractable":[107],"information\u2014while":[108],"explicitly":[109],"decoupling":[110],"roles":[112],"(information":[115],"source)":[116],"computation":[118],"(extraction":[119],"mechanism).":[120],"A":[121],"finite-data":[122],"saturation":[123],"formalizes":[125],"compute":[127],"cannot":[128],"extract":[129],"more":[130],"than":[133],"exists":[134],"show":[139],"penalizes":[142],"overfitting":[143],"through":[144],"generalization":[146],"gap,":[147],"distinguishing":[148],"genuine":[149],"memorization.":[152],"These":[153],"results":[154],"as":[157],"rigorous":[159],"foundation":[160],"for":[161],"quantifying":[162],"systems":[167],"operating":[168],"datasets.":[171],"An":[172],"extended":[173],"version":[174],"appears":[175],"at":[176],"arXiv:2601.04728.":[177]},"counts_by_year":[],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2026-08-26T00:00:00"}