{"id":"https://openalex.org/W7162453115","doi":"https://doi.org/10.48550/arxiv.2605.25608","title":"Learning Sparse Compositional Functions with Norm-Constrained Neural Networks","display_name":"Learning Sparse Compositional Functions with Norm-Constrained Neural Networks","publication_year":2026,"publication_date":"2026-05-25","ids":{"openalex":"https://openalex.org/W7162453115","doi":"https://doi.org/10.48550/arxiv.2605.25608"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.25608","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25608","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":null,"license_id":null,"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.2605.25608","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137081689","display_name":"Shuo Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Shuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137002978","display_name":"Lorenzo Fiorito","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fiorito, Lorenzo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061220999","display_name":"Lorenzo Rosasco","orcid":"https://orcid.org/0000-0003-3098-383X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rosasco, Lorenzo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137074919","display_name":"Tomaso Poggio","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Poggio, Tomaso","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/T11273","display_name":"Advanced Graph Neural Networks","score":0.421999990940094,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.421999990940094,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.07360000163316727,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.07209999859333038,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.5806000232696533},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5468999743461609},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5367000102996826},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45010000467300415},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.42590001225471497},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4122999906539917},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3792000114917755},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.37610000371932983},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.35420000553131104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5914999842643738},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5806000232696533},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5468999743461609},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5367000102996826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4878000020980835},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.42590001225471497},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4122999906539917},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38530001044273376},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3538999855518341},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.33230000734329224},{"id":"https://openalex.org/C197855036","wikidata":"https://www.wikidata.org/wiki/Q380172","display_name":"Binary tree","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3073999881744385},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28619998693466187},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C2781147490","wikidata":"https://www.wikidata.org/wiki/Q5156808","display_name":"Compositional data","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C9870796","wikidata":"https://www.wikidata.org/wiki/Q490481","display_name":"Turing","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C37616216","wikidata":"https://www.wikidata.org/wiki/Q3218363","display_name":"Lasso (programming language)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.25608","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25608","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.25608","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25608","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,143],"ability":[1],"of":[2,48,58,130,156],"deep":[3,104,149],"neural":[4,105],"networks":[5,150],"to":[6],"learn":[7],"hierarchical":[8,165],"features":[9],"is":[10,94,116],"widely":[11],"regarded":[12],"as":[13],"a":[14,66,128],"key":[15],"mechanism":[16],"underlying":[17],"their":[18],"success":[19],"in":[20],"high-dimensional":[21],"learning.":[22],"Existing":[23],"theory":[24],"partially":[25],"supports":[26],"this":[27,76],"view":[28],"by":[29,96],"establishing":[30],"approximation":[31,80],"rates":[32,81,144],"based":[33],"on":[34],"parameter":[35,73],"counts":[36],"and":[37,82,139],"sample":[38,62],"complexity":[39,70],"guarantees":[40],"for":[41,86],"compositional":[42,89,92,122,141,154],"models":[43],"without":[44],"incurring":[45],"the":[46,56,61,72,153,157,162],"curse":[47],"dimensionality":[49],"(CoD).":[50],"To":[51],"study":[52],"overparameterized":[53],"regimes,":[54],"where":[55],"number":[57],"parameters":[59],"exceeds":[60],"size,":[63],"we":[64,78,126,145],"develop":[65],"framework":[67],"that":[68,115,148],"measures":[69],"via":[71],"norm.":[74],"Within":[75],"approach,":[77],"establish":[79],"excess":[83],"risk":[84],"bounds":[85],"learning":[87],"sparse":[88,121],"functions":[90],"whose":[91],"structure":[93,155],"represented":[95],"directed":[97],"acyclic":[98],"graphs":[99],"(DAGs),":[100],"using":[101],"Frobenius":[102],"norm-constrained":[103],"networks.":[106],"Our":[107],"results":[108],"have":[109],"broad":[110],"applicability":[111],"since":[112],"every":[113],"function":[114],"efficiently":[117],"Turing":[118],"computable":[119],"admits":[120],"representations.":[123,166],"In":[124],"particular,":[125],"cover":[127],"range":[129],"representative":[131],"models,":[132,135],"including":[133],"multi-index":[134],"binary":[136],"tree":[137],"structures,":[138],"general":[140],"architectures.":[142],"derive":[146],"show":[147],"can":[151],"exploit":[152],"target":[158],"functions,":[159],"effectively":[160],"avoiding":[161],"CoD":[163],"through":[164]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-27T00:00:00"}