{"id":"https://openalex.org/W7161768093","doi":"https://doi.org/10.48550/arxiv.2605.19122","title":"Dual-Channel Tensor Neural Networks: Finite-Sample Theory and Conformal Structure Selection","display_name":"Dual-Channel Tensor Neural Networks: Finite-Sample Theory and Conformal Structure Selection","publication_year":2026,"publication_date":"2026-05-18","ids":{"openalex":"https://openalex.org/W7161768093","doi":"https://doi.org/10.48550/arxiv.2605.19122"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.19122","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19122","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.19122","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136514761","display_name":"Elynn Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Elynn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136509541","display_name":"Jiayu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiayu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136552734","display_name":"Zheshi Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Zheshi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060646545","display_name":"Jian Pei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei, Jian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9742000102996826,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9742000102996826,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.006200000178068876,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.00559999980032444,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.8281000256538391},{"id":"https://openalex.org/keywords/multilinear-map","display_name":"Multilinear map","score":0.7080000042915344},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5231999754905701},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5127999782562256},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.499099999666214},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4666000008583069},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.44179999828338623},{"id":"https://openalex.org/keywords/conformal-map","display_name":"Conformal map","score":0.4345000088214874},{"id":"https://openalex.org/keywords/multilinear-algebra","display_name":"Multilinear algebra","score":0.4180000126361847}],"concepts":[{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.8281000256538391},{"id":"https://openalex.org/C84392682","wikidata":"https://www.wikidata.org/wiki/Q1952404","display_name":"Multilinear map","level":2,"score":0.7080000042915344},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5231999754905701},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5127999782562256},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.499099999666214},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.47099998593330383},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4666000008583069},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.44179999828338623},{"id":"https://openalex.org/C98214594","wikidata":"https://www.wikidata.org/wiki/Q850275","display_name":"Conformal map","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C60321788","wikidata":"https://www.wikidata.org/wiki/Q1197190","display_name":"Multilinear algebra","level":5,"score":0.4180000126361847},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4083000123500824},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4034000039100647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.385699987411499},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.25619998574256897},{"id":"https://openalex.org/C51255310","wikidata":"https://www.wikidata.org/wiki/Q1163016","display_name":"Tensor product","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C42704193","wikidata":"https://www.wikidata.org/wiki/Q7851097","display_name":"Tucker decomposition","level":4,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.19122","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19122","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2605.19122","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19122","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"id":"https://metadata.un.org/sdg/13","score":0.8656597137451172,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tensor-valued":[0],"data":[1],"arise":[2],"naturally":[3],"in":[4],"neuroimaging,":[5],"genomics,":[6],"climate":[7],"science,":[8],"and":[9,67,71,84,88,113,116,129,155,158,194,208],"spatiotemporal":[10],"networks,":[11],"where":[12],"multilinear":[13],"dependencies":[14],"across":[15],"modes":[16],"carry":[17],"information":[18],"that":[19,58,106,118,148],"is":[20,82,122,179],"destroyed":[21],"under":[22],"vectorization.":[23],"Existing":[24],"approaches":[25],"either":[26],"impose":[27],"a":[28,42,52,64,68,92,143,171,198],"single":[29,93],"low-rank":[30,65],"structure,":[31],"which":[32,45],"can":[33],"miss":[34],"localized":[35],"signal,":[36],"or":[37],"treat":[38],"the":[39,73,103,119,126,135,151,180,212],"tensor":[40,61,137,188,213],"as":[41],"long":[43],"vector,":[44],"discards":[46],"its":[47],"multiway":[48],"geometry.":[49],"We":[50],"propose":[51,170],"*Dual-Channel":[53],"Tensor":[54],"Neural":[55],"Network*":[56],"(DC-TNN)":[57],"decomposes":[59],"each":[60],"input":[62],"into":[63,108],"core":[66,111,127],"sparse":[69],"refinement,":[70],"processes":[72],"two":[74],"components":[75],"through":[76],"coupled":[77],"neural":[78],"channels.":[79],"The":[80],"framework":[81],"structure-agnostic":[83],"accommodates":[85],"CP,":[86],"Tucker,":[87],"tensor-train":[89],"cores":[90],"within":[91,150],"architecture.":[94],"For":[95,139],"estimation,":[96,112],"we":[97,141,169],"establish":[98],"non-asymptotic":[99],"risk":[100],"bounds":[101],"for":[102,184],"DC-TNN":[104],"estimator":[105],"decompose":[107],"network":[109],"approximation,":[110],"refinement-selection":[114],"terms,":[115],"show":[117],"effective":[120],"dimension":[121],"determined":[123],"jointly":[124],"by":[125,134],"rank":[128],"refinement":[130],"sparsity":[131],"rather":[132],"than":[133],"ambient":[136],"size.":[138],"inference,":[140],"develop":[142],"*structure-aware":[144],"conformal":[145],"ROC*":[146],"procedure":[147],"calibrates":[149],"core-refinement":[152],"latent":[153],"space":[154],"produces":[156],"ROC":[157],"AUC":[159],"confidence":[160],"bands":[161],"with":[162,190],"finite-sample,":[163],"distribution-free":[164,182],"coverage.":[165],"Building":[166],"on":[167],"this,":[168],"*conformal":[172],"structure":[173],"selector*":[174],"that,":[175],"to":[176],"our":[177],"knowledge,":[178],"*first":[181],"procedure*":[183],"choosing":[185],"among":[186],"candidate":[187],"decompositions":[189],"finite-sample":[191],"validity.":[192],"Simulations":[193],"an":[195],"analysis":[196],"of":[197,211],"protein":[199],"dataset":[200],"demonstrate":[201],"competitive":[202],"predictive":[203],"accuracy,":[204],"reliable":[205],"uncertainty":[206],"quantification,":[207],"consistent":[209],"recovery":[210],"structure.":[214]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-21T00:00:00"}