{"id":"https://openalex.org/W7123877496","doi":"https://doi.org/10.1109/isit62367.2026.11653954","title":"Generalization Bounds for Transformer Channel Decoders","display_name":"Generalization Bounds for Transformer Channel Decoders","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7123877496","doi":"https://doi.org/10.1109/isit62367.2026.11653954"},"language":null,"primary_location":{"id":"doi:10.1109/isit62367.2026.11653954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit62367.2026.11653954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2601.06969","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082358513","display_name":"Qinshan Zhang","orcid":"https://orcid.org/0009-0005-2502-3369"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinshan Zhang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122980501","display_name":"Bin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Chen","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122988159","display_name":"Yong Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Jiang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122910739","display_name":"Shu-Tao Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu-Tao Xia","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":23.0502,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96779809,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":97},"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/T10125","display_name":"Advanced Wireless Communication Techniques","score":0.37619999051094055,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10125","display_name":"Advanced Wireless Communication Techniques","score":0.37619999051094055,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12131","display_name":"Wireless Signal Modulation Classification","score":0.2732999920845032,"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/T11321","display_name":"Error Correcting Code Techniques","score":0.23109999299049377,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/generalization","display_name":"Generalization","score":0.7293999791145325},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5924999713897705},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.47920000553131104},{"id":"https://openalex.org/keywords/generalization-error","display_name":"Generalization error","score":0.4424000084400177},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.439300000667572},{"id":"https://openalex.org/keywords/multiplicative-function","display_name":"Multiplicative function","score":0.4221000075340271}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7293999791145325},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5924999713897705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5210999846458435},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.47920000553131104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46239998936653137},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.4424000084400177},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3695000112056732},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.337799996137619},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3142000138759613},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isit62367.2026.11653954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit62367.2026.11653954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},{"id":"doi:10.48550/arxiv.2601.06969","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.06969","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2601.06969","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.06969","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2169732368","https://openalex.org/W2626778328","https://openalex.org/W2666368276","https://openalex.org/W2963408536","https://openalex.org/W2963836746","https://openalex.org/W2964070430","https://openalex.org/W2964175260","https://openalex.org/W3031023929","https://openalex.org/W3112330636","https://openalex.org/W3112949451","https://openalex.org/W3160306825","https://openalex.org/W3161746554","https://openalex.org/W4256264271","https://openalex.org/W4285817698","https://openalex.org/W4290996380","https://openalex.org/W4312732721","https://openalex.org/W4387870194","https://openalex.org/W4391429601","https://openalex.org/W4401692993","https://openalex.org/W4409325802","https://openalex.org/W4415368862","https://openalex.org/W7123877496","https://openalex.org/W7133205069"],"related_works":[],"abstract_inverted_index":{"Transformer":[0,9],"channel":[1,17],"decoders,":[2],"such":[3],"as":[4],"the":[5,29,56,67,97,107,115],"Error":[6],"Correction":[7],"Code":[8],"(ECCT),":[10],"have":[11],"shown":[12],"strong":[13],"empirical":[14],"performance":[15,31],"in":[16],"decoding,":[18],"yet":[19],"their":[20],"generalization":[21,30,57,104,118],"behavior":[22],"remains":[23],"theoretically":[24],"unclear.":[25],"This":[26],"paper":[27],"studies":[28],"of":[32,109,123],"ECCT":[33],"from":[34],"a":[35,40,102],"learning-theoretic":[36],"perspective.":[37],"By":[38],"establishing":[39],"connection":[41],"between":[42],"multiplicative":[43],"noise":[44],"estimation":[45],"errors":[46],"and":[47,74,78,83],"bit-error-rate":[48],"(BER),":[49],"we":[50],"derive":[51],"an":[52],"upper":[53],"bound":[54,65],"on":[55,69],"gap":[58],"via":[59],"bit-wise":[60],"Rademacher":[61],"complexity.":[62],"The":[63],"resulting":[64],"characterizes":[66],"dependence":[68],"code":[70],"length,":[71],"model":[72],"parameters,":[73],"training":[75],"set":[76],"size,":[77],"applies":[79],"to":[80,101],"both":[81],"single-layer":[82],"multi-layer":[84],"ECCTs.":[85],"We":[86],"further":[87],"show":[88],"that":[89,95],"parity-check-based":[90],"masked":[91],"attention":[92],"induces":[93],"sparsity":[94],"reduces":[96],"covering":[98],"number,":[99],"leading":[100],"tighter":[103],"bound.":[105],"To":[106],"best":[108],"our":[110],"knowledge,":[111],"this":[112,121],"work":[113],"provides":[114],"first":[116],"theoretical":[117],"guarantees":[119],"for":[120],"class":[122],"decoders.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2026-01-14T00:00:00"}
