{"id":"https://openalex.org/W7164914693","doi":"https://doi.org/10.48550/arxiv.2606.15219","title":"Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model","display_name":"Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model","publication_year":2026,"publication_date":"2026-06-13","ids":{"openalex":"https://openalex.org/W7164914693","doi":"https://doi.org/10.48550/arxiv.2606.15219"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.15219","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15219","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.2606.15219","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138704502","display_name":"Siyu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Siyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138741890","display_name":"Beining Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Beining","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110128334","display_name":"M A \u00c7ipilo lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Miao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138721461","display_name":"Zhuoran Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zhuoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138720648","display_name":"Tianhao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Tianhao","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":0.2985000014305115,"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":0.2985000014305115,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.21610000729560852,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11649999767541885,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.6385999917984009},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5554999709129333},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5101000070571899},{"id":"https://openalex.org/keywords/exponent","display_name":"Exponent","score":0.48980000615119934},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.44749999046325684},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4327000081539154},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.391400009393692},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3873000144958496},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3635999858379364}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6385999917984009},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5554999709129333},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5101000070571899},{"id":"https://openalex.org/C2780388253","wikidata":"https://www.wikidata.org/wiki/Q5421508","display_name":"Exponent","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48339998722076416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48069998621940613},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.44749999046325684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4422000050544739},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4327000081539154},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41449999809265137},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3635999858379364},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.31369999051094055},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.29170000553131104},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.2822999954223633},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.26429998874664307},{"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/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25859999656677246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.15219","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15219","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.2606.15219","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15219","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,67],"work,":[2],"we":[3,85,160],"tackle":[4],"the":[5,16,34,46,50,55,132,144,165,184,209],"following":[6],"question:":[7],"Can":[8],"neural":[9,63,95],"networks":[10,64],"trained":[11],"with":[12,131,136],"gradient-based":[13,89,220],"methods":[14],"achieve":[15,66],"optimal":[17],"computational-statistical":[18],"tradeoff":[19],"in":[20,97],"learning":[21,54,82],"Gaussian":[22],"single-index":[23,83],"models?":[24],"Prior":[25],"research":[26],"has":[27],"shown":[28],"that":[29,121,128,182],"any":[30],"polynomial-time":[31],"algorithm":[32,90,123],"under":[33],"statistical":[35],"query":[36],"(SQ)":[37],"framework":[38],"requires":[39],"$\u03a9(d^{s^\\star/2}\\lor":[40],"d)$":[41],"samples,":[42],"where":[43,167],"$s^\\star$":[44],"is":[45,102,169,213],"generative":[47,155],"exponent":[48],"representing":[49],"intrinsic":[51],"difficulty":[52],"of":[53,107,116,194,214],"underlying":[56],"model.":[57],"However,":[58],"it":[59],"remains":[60],"unknown":[61,133],"whether":[62],"can":[65],"sample":[68,137],"complexity.":[69],"Inspired":[70],"by":[71,175,198],"prior":[72],"techniques":[73],"such":[74,225],"as":[75,226],"label":[76],"transformation":[77],"and":[78,109,217],"landscape":[79],"smoothing":[80],"for":[81,91,153,171],"models,":[84],"propose":[86],"a":[87,93,105,113,125,150,177,189,203],"unified":[88],"training":[92],"two-layer":[94],"network":[96],"polynomial":[98],"time.":[99],"Our":[100,206],"method":[101,200],"adaptable":[103],"to":[104,149,164,202,222],"variety":[106],"loss":[108],"activation":[110],"functions,":[111],"covering":[112],"broad":[114],"class":[115],"existing":[117],"approaches.":[118],"We":[119,187],"show":[120],"our":[122,162,199],"learns":[124],"feature":[126],"representation":[127],"strongly":[129],"aligns":[130],"signal":[134],"$\u03b8^\\star$,":[135],"complexity":[138],"$\\widetilde{O}":[139],"(d^{s^\\star/2}":[140],"\\lor":[141],"d)$,":[142],"matching":[143],"SQ":[145,191],"lower":[146,192],"bound":[147,193],"up":[148,201],"polylogarithmic":[151,204],"factor":[152],"all":[154],"exponents":[156],"$s^\\star\\geq":[157],"1$.":[158],"Furthermore,":[159],"extend":[161],"approach":[163],"setting":[166],"$\u03b8^\\star$":[168],"$k$-sparse":[170],"$k":[172],"=":[173],"o(\\sqrt{d})$":[174],"introducing":[176],"novel":[178],"weight":[179,210],"perturbation":[180,211],"technique":[181],"leverages":[183],"sparsity":[185],"structure.":[186],"derive":[188],"corresponding":[190],"order":[195],"$\\widetilde\u03a9(k^{s^\\star})$,":[196],"matched":[197],"factor.":[205],"framework,":[207],"especially":[208],"technique,":[212],"independent":[215],"interest,":[216],"suggests":[218],"potential":[219],"solutions":[221],"other":[223],"problems":[224],"sparse":[227],"tensor":[228],"PCA.":[229]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-17T00:00:00"}