{"id":"https://openalex.org/W2113517874","doi":null,"title":"Learning Polynomials with Neural Networks","display_name":"Learning Polynomials with Neural Networks","publication_year":2014,"publication_date":"2014-06-21","ids":{"openalex":"https://openalex.org/W2113517874","mag":"2113517874"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.987.4244","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.987.4244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://machinelearning.wustl.edu/mlpapers/paper_files/icml2014c2_andoni14.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088346829","display_name":"Alexandr Andoni","orcid":"https://orcid.org/0009-0004-8042-0976","observed_orcids":["https://orcid.org/0009-0004-8042-0976"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandr Andoni","raw_affiliation_strings":["Microsoft research#TAB#"],"raw_orcid":"https://orcid.org/0009-0004-8042-0976","affiliations":[{"raw_affiliation_string":"Microsoft research#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085651536","display_name":"Rina Panigrahy","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rina Panigrahy\u200e","raw_affiliation_strings":["Microsoft research#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft research#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079503799","display_name":"Gregory J. Valiant","orcid":"https://orcid.org/0000-0002-2211-1073","observed_orcids":["https://orcid.org/0000-0002-2211-1073"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory Valiant","raw_affiliation_strings":["Stanford University"],"raw_orcid":"https://orcid.org/0000-0002-2211-1073","affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":null,"display_name":"Li Zhang","orcid":"https://orcid.org/0000-0001-7914-0679","observed_orcids":["https://orcid.org/0000-0001-7914-0679"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["Microsoft research#TAB#"],"raw_orcid":"https://orcid.org/0000-0001-7914-0679","affiliations":[{"raw_affiliation_string":"Microsoft research#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.0519,"has_fulltext":false,"cited_by_count":116,"citation_normalized_percentile":{"value":0.97763218,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1908","last_page":"1916"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9247999787330627,"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/T10320","display_name":"Neural Networks and Applications","score":0.9247999787330627,"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":0.07050000131130219,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.001500000013038516,"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/neural-network","display_name":"artificial neural networks","score":0.7829999923706055},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"gradient descent","score":0.9570000171661377},{"id":"https://openalex.org/keywords/two-layer-neural-networks","display_name":"two-layer neural networks","score":0.8289999961853027},{"id":"https://openalex.org/keywords/local-minima","display_name":"local minima","score":0.7519999742507935},{"id":"https://openalex.org/keywords/random-initialization","display_name":"random initialization","score":0.8109999895095825},{"id":"https://openalex.org/keywords/complex-valued-weights","display_name":"complex-valued weights","score":0.9549999833106995},{"id":"https://openalex.org/keywords/sparse-polynomials","display_name":"sparse polynomials","score":0.875},{"id":"https://openalex.org/keywords/theoretical-guarantees","display_name":"theoretical guarantees","score":0.47200000286102295}],"concepts":[{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.87413090467453},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.791570782661438},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.7666085958480835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5656530261039734},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.4970836937427521},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4696618318557739},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.42111632227897644},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4210605323314667},{"id":"https://openalex.org/C177973122","wikidata":"https://www.wikidata.org/wiki/Q7860946","display_name":"Types of artificial neural networks","level":4,"score":0.41204720735549927},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.4115750193595886},{"id":"https://openalex.org/C86582703","wikidata":"https://www.wikidata.org/wiki/Q7617824","display_name":"Stochastic neural network","level":4,"score":0.41031062602996826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3945157527923584},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38219618797302246},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.370564341545105},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.2748245596885681},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.987.4244","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.987.4244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://machinelearning.wustl.edu/mlpapers/paper_files/icml2014c2_andoni14.pdf","raw_type":"text"},{"id":"mag:2113517874","doi":null,"is_oa":false,"landing_page_url":"http://jmlr.org/proceedings/papers/v32/andoni14.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W1613249581","https://openalex.org/W1972913305","https://openalex.org/W1973631422","https://openalex.org/W1984459117","https://openalex.org/W2058785578","https://openalex.org/W2061949491","https://openalex.org/W2072128103","https://openalex.org/W2110798204","https://openalex.org/W2125930537","https://openalex.org/W2136922672","https://openalex.org/W2163605009","https://openalex.org/W2166116275","https://openalex.org/W2171001107","https://openalex.org/W2172174689","https://openalex.org/W2239255512","https://openalex.org/W2294059674"],"related_works":["https://openalex.org/W2800987155","https://openalex.org/W7140216689","https://openalex.org/W7133198840","https://openalex.org/W2966363981","https://openalex.org/W1526092162","https://openalex.org/W7103748654","https://openalex.org/W4404976256","https://openalex.org/W7117256368","https://openalex.org/W2925259031","https://openalex.org/W2798291370"],"abstract_inverted_index":{"We":[0,87],"study":[1],"the":[2,13,82,94,105,132,145,174,210,214,217],"effectiveness":[3],"of":[4,68,84,100,216],"learning":[5,38],"low":[6,139],"degree":[7,140],"polynomials":[8,201],"using":[9],"neural":[10,18,39,85,91,125,175,207],"networks":[11,19,92],"by":[12,183],"gradi-ent":[14],"descent":[15,30,57,135],"method.":[16],"While":[17],"have":[20,24],"been":[21,32],"shown":[22],"to":[23,80,114],"great":[25],"expressive":[26],"power,":[27],"and":[28,104],"gradient":[29,56,134],"has":[31],"widely":[33],"used":[34],"in":[35],"prac-tice":[36],"for":[37,46,65,121,193],"networks,":[40,208],"few":[41],"theoretical":[42,78],"guarantees":[43],"are":[44,169],"known":[45,54],"such":[47],"methods.":[48],"In":[49,71],"par-ticular,":[50],"it":[51],"is":[52,97,109],"well":[53],"that":[55,120,151],"can":[58,160,177,202],"get":[59],"stuck":[60],"at":[61],"local":[62,181],"minima,":[63],"even":[64],"simple":[66],"classes":[67],"target":[69,158,218],"functions.":[70],"this":[72],"paper,":[73],"we":[74,118,143,149,153,197],"present":[75],"sev-eral":[76],"positive":[77],"results":[79],"support":[81],"ef-fectiveness":[83],"networks.":[86],"focus":[88],"on":[89,213],"two-layer":[90],"where":[93],"bottom":[95],"layer":[96,107],"a":[98,110,122,180,185],"set":[99],"non-linear":[101],"hidden":[102,130],"nodes,":[103],"top":[106],"node":[108],"linear":[111],"function,":[112],"similar":[113],"Bar-ron":[115],"(1993).":[116],"First":[117],"show":[119,150],"randomly":[123],"initialized":[124],"network":[126,176],"with":[127,205,209],"sufficiently":[128],"many":[129],"units,":[131],"generic":[133],"algo-rithm":[136],"learns":[137],"any":[138],"polynomial,":[141],"assum-ing":[142],"initialize":[144],"weights":[146,156],"randomly.":[147],"Secondly,":[148],"if":[152],"use":[154],"complex-valued":[155],"(the":[157],"function":[159],"still":[161],"be":[162,203],"real),":[163],"then":[164],"un-der":[165],"suitable":[166],"conditions,":[167],"there":[168],"no":[170],"\u201crobust":[171],"lo-cal":[172],"minima\u201d:":[173],"always":[178],"es-cape":[179],"minimum":[182],"performing":[184],"random":[186],"perturbation.":[187],"This":[188],"property":[189],"does":[190],"not":[191],"hold":[192],"real-valued":[194],"weights.":[195],"Thirdly,":[196],"discuss":[198],"whether":[199],"sparse":[200],"learned":[204],"small":[206],"size":[211],"dependent":[212],"sparsity":[215],"function.":[219]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}