{"id":"https://openalex.org/W3012806192","doi":null,"title":"A classification for the performance of online SGD for high-dimensional inference.","display_name":"A classification for the performance of online SGD for high-dimensional inference.","publication_year":2020,"publication_date":"2020-03-23","ids":{"openalex":"https://openalex.org/W3012806192","mag":"3012806192"},"language":"en","primary_location":{"id":"mag:3012806192","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2003.10409","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.10409","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039747459","display_name":"G\u00e9rard Ben Arous","orcid":"https://orcid.org/0000-0001-5599-8726","observed_orcids":["https://orcid.org/0000-0001-5599-8726"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G\u00e9rard Ben Arous","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5599-8726","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085479654","display_name":"Reza Gheissari","orcid":"https://orcid.org/0000-0003-4236-9407","observed_orcids":["https://orcid.org/0000-0003-4236-9407"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reza Gheissari","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4236-9407","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051194866","display_name":"Aukosh Jagannath","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aukosh Jagannath","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":2,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9911999702453613,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9911999702453613,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.0015999999595806003,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10136","display_name":"Statistical Methods and Inference","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/high-dimensional-inference","display_name":"high-dimensional inference","score":0.9129999876022339},{"id":"https://openalex.org/keywords/weak-recovery","display_name":"weak recovery","score":0.9919999837875366},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"sample complexity","score":0.6019999980926514},{"id":"https://openalex.org/keywords/nonconvex-optimization","display_name":"non-convex optimization","score":0.8190000057220459},{"id":"https://openalex.org/keywords/generalized-linear-models","display_name":"generalized linear models","score":0.8650000095367432},{"id":"https://openalex.org/keywords/gaussian-mixture-model","display_name":"Gaussian mixture model","score":0.9089999794960022},{"id":"https://openalex.org/keywords/phase-retrieval","display_name":"phase retrieval","score":0.9990000128746033},{"id":"https://openalex.org/keywords/tensor-models","display_name":"tensor models","score":0.8040000200271606},{"id":"https://openalex.org/keywords/single-layer-neural-network","display_name":"single-layer neural network","score":0.8679999709129333},{"id":"https://openalex.org/keywords/activation-functions","display_name":"activation functions","score":0.5289999842643738},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"supervised learning","score":0.4740000069141388}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6395472288131714},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5684071779251099},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.519723653793335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4807950556278229},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4507914185523987},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4461555778980255},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4374655783176422},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4348374307155609},{"id":"https://openalex.org/C2780388253","wikidata":"https://www.wikidata.org/wiki/Q5421508","display_name":"Exponent","level":2,"score":0.42709988355636597},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.42666542530059814},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3872256875038147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35802751779556274},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3297628164291382},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16888383030891418},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14765426516532898},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3012806192","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2003.10409","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3012806192","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2003.10409","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W1491706803","https://openalex.org/W1520752838","https://openalex.org/W1521197246","https://openalex.org/W1554944419","https://openalex.org/W1644055776","https://openalex.org/W1697075315","https://openalex.org/W1994616650","https://openalex.org/W2050583479","https://openalex.org/W2063588877","https://openalex.org/W2066459155","https://openalex.org/W2079705627","https://openalex.org/W2083459869","https://openalex.org/W2090980101","https://openalex.org/W2102486516","https://openalex.org/W2112796928","https://openalex.org/W2125812768","https://openalex.org/W2127300249","https://openalex.org/W2132211083","https://openalex.org/W2162287622","https://openalex.org/W2164071215","https://openalex.org/W2283023501","https://openalex.org/W2290522125","https://openalex.org/W2508844316","https://openalex.org/W2557283755","https://openalex.org/W2566337607","https://openalex.org/W2585411378","https://openalex.org/W2589022458","https://openalex.org/W2590513847","https://openalex.org/W2593262341","https://openalex.org/W2725016515","https://openalex.org/W2730184663","https://openalex.org/W2768480272","https://openalex.org/W2772785876","https://openalex.org/W2790687101","https://openalex.org/W2792812004","https://openalex.org/W2795594425","https://openalex.org/W2801490189","https://openalex.org/W2802698595","https://openalex.org/W2886093850","https://openalex.org/W2891786606","https://openalex.org/W2899900971","https://openalex.org/W2900900389","https://openalex.org/W2913887546","https://openalex.org/W2918745211","https://openalex.org/W2933703783","https://openalex.org/W2946273996","https://openalex.org/W2947984106","https://openalex.org/W2949977662","https://openalex.org/W2954063644","https://openalex.org/W2962881498","https://openalex.org/W2962915600","https://openalex.org/W2963122491","https://openalex.org/W2963595633","https://openalex.org/W2964038363","https://openalex.org/W2965944281","https://openalex.org/W2981804444","https://openalex.org/W2993730048","https://openalex.org/W2994147529","https://openalex.org/W3008596124","https://openalex.org/W3023124831","https://openalex.org/W3034877436","https://openalex.org/W3043072433","https://openalex.org/W3046968338","https://openalex.org/W3101975788","https://openalex.org/W3102511045","https://openalex.org/W4212863985","https://openalex.org/W4240234826"],"related_works":["https://openalex.org/W3100482347","https://openalex.org/W4416248574","https://openalex.org/W4416429438","https://openalex.org/W4386722276","https://openalex.org/W4413182473","https://openalex.org/W7133208588","https://openalex.org/W3013593644","https://openalex.org/W4378942444","https://openalex.org/W3119796929","https://openalex.org/W2786323440"],"abstract_inverted_index":{"Stochastic":[0],"gradient":[1],"descent":[2],"(SGD)":[3],"is":[4,43,71,81,111],"a":[5,26,37,74,96,112,197,243],"popular":[6],"algorithm":[7,70],"for":[8,123,207,228],"optimization":[9],"problems":[10],"arising":[11],"in":[12,63,126,251],"high-dimensional":[13],"inference":[14],"tasks.":[15],"Here":[16],"one":[17,173],"produces":[18],"an":[19,22,143],"estimator":[20],"of":[21,29,32,54,58,91,114,117,120,128,131,146,200,245,248,253,257],"unknown":[23,103],"parameter":[24,205],"from":[25,73],"large":[27],"number":[28,130],"independent":[30],"samples":[31,132,180],"data":[33],"by":[34,193],"iteratively":[35],"optimizing":[36],"loss":[38,41,79],"function.":[39,260],"This":[40,138],"function":[42],"high-dimensional,":[44],"random,":[45],"and":[46,77,170,177,217,220],"often":[47],"complex.":[48],"We":[49,189],"study":[50],"here":[51],"the":[52,55,64,69,78,89,102,115,129,135,147,153,157,182,246,254,258],"performance":[53,90],"simplest":[56],"version":[57],"SGD,":[59,62],"namely":[60],"online":[61,92,124],"initial":[65],"search":[66],"phase,":[67],"where":[68],"far":[72],"trust":[75],"region":[76],"landscape":[80],"highly":[82],"non-convex.":[83],"To":[84],"this":[85,121,236,249],"end,":[86],"we":[87,151,160],"investigate":[88],"SGD":[93,125],"at":[94],"attaining":[95],"better":[97],"than":[98],"random":[99],"correlation":[100],"with":[101,231],"parameter,":[104],"i.e,":[105],"achieving":[106],"weak":[107,187],"recovery.":[108,188],"\r\nOur":[109],"contribution":[110],"classification":[113,139,244],"difficulty":[116,247],"typical":[118],"instances":[119],"task":[122,250],"terms":[127,252],"required":[133],"as":[134,204,223,225],"dimension":[136],"diverges.":[137],"depends":[140],"only":[141],"on":[142],"intrinsic":[144],"property":[145],"population":[148],"loss,":[149],"which":[150],"call":[152],"information":[154,158],"exponent.":[155],"Using":[156],"exponent,":[159],"find":[161],"that":[162],"there":[163],"are":[164],"three":[165],"distinct":[166],"regimes---the":[167],"easy,":[168],"critical,":[169],"difficult":[171],"regimes---where":[172],"requires":[174],"linear,":[175],"quasilinear,":[176],"polynomially":[178],"many":[179],"(in":[181],"dimension)":[183],"respectively":[184],"to":[185,196],"achieve":[186],"illustrate":[190],"our":[191,239],"approach":[192],"applying":[194],"it":[195],"wide":[198],"variety":[199],"estimation":[201,206],"tasks":[202],"such":[203],"generalized":[208],"linear":[209],"models,":[210,214,222],"two-component":[211],"Gaussian":[212],"mixture":[213],"phase":[215],"retrieval,":[216],"spiked":[218],"matrix":[219],"tensor":[221],"well":[224],"supervised":[226],"learning":[227],"single-layer":[229],"networks":[230],"general":[232],"activation":[233,259],"functions.":[234],"In":[235],"latter":[237],"case,":[238],"results":[240],"translate":[241],"into":[242],"Hermite":[255],"decomposition":[256]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-03-27T00:00:00"}