{"id":"https://openalex.org/W3015871848","doi":"https://doi.org/10.1109/icassp40776.2020.9054014","title":"Lookahead Converges to Stationary Points of Smooth Non-convex Functions","display_name":"Lookahead Converges to Stationary Points of Smooth Non-convex Functions","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015871848","doi":"https://doi.org/10.1109/icassp40776.2020.9054014","mag":"3015871848"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5100398977","display_name":"Jianyu Wang","orcid":"https://orcid.org/0000-0002-7075-9333"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jianyu Wang","raw_affiliation_strings":["Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074049737","display_name":"Vinayak Tantia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vinayak Tantia","raw_affiliation_strings":["Facebook AI Research, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Montreal, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057065873","display_name":"Nicolas Ballas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicolas Ballas","raw_affiliation_strings":["Facebook AI Research, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Montreal, Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089819604","display_name":"Michael Rabbat","orcid":"https://orcid.org/0000-0003-0536-7904"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Rabbat","raw_affiliation_strings":["Facebook AI Research, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Montreal, Canada","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100398977"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.6628,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7506453,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"106","issue":null,"first_page":"8604","last_page":"8608"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.631008505821228},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.5623351335525513},{"id":"https://openalex.org/keywords/stationary-point","display_name":"Stationary point","score":0.5408307909965515},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5214704275131226},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4781535565853119},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4671708047389984},{"id":"https://openalex.org/keywords/convex-function","display_name":"Convex function","score":0.44902855157852173},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4140751361846924},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28887030482292175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19971799850463867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.631008505821228},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.5623351335525513},{"id":"https://openalex.org/C189237950","wikidata":"https://www.wikidata.org/wiki/Q2500758","display_name":"Stationary point","level":2,"score":0.5408307909965515},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5214704275131226},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4781535565853119},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4671708047389984},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.44902855157852173},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4140751361846924},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28887030482292175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19971799850463867},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2012445782","https://openalex.org/W2027481851","https://openalex.org/W2063403497","https://openalex.org/W2137435346","https://openalex.org/W2160815625","https://openalex.org/W2194775991","https://openalex.org/W2622263826","https://openalex.org/W2888561381","https://openalex.org/W2902410171","https://openalex.org/W2953881522","https://openalex.org/W2962771678","https://openalex.org/W2963403868","https://openalex.org/W2963433607","https://openalex.org/W2964121744","https://openalex.org/W2964153283","https://openalex.org/W2970803838","https://openalex.org/W2977517840","https://openalex.org/W2996693845","https://openalex.org/W3212066104","https://openalex.org/W4299802343","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6739622702","https://openalex.org/W6739901393","https://openalex.org/W6754143808","https://openalex.org/W6756976665","https://openalex.org/W6766196973","https://openalex.org/W6768660345"],"related_works":["https://openalex.org/W2985635587","https://openalex.org/W2391251536","https://openalex.org/W2362198218","https://openalex.org/W2007224728","https://openalex.org/W1982750869","https://openalex.org/W2019521278","https://openalex.org/W1984922432","https://openalex.org/W2113077220","https://openalex.org/W4387635768","https://openalex.org/W2604676813"],"abstract_inverted_index":{"The":[0],"Lookahead":[1,24,64,75,90],"optimizer":[2],"[Zhang":[3],"et":[4],"al.,":[5],"2019]":[6],"was":[7],"recently":[8],"proposed":[9],"and":[10,43,78],"demonstrated":[11],"to":[12,66],"improve":[13],"performance":[14],"of":[15,62,70],"stochastic":[16],"first-order":[17],"methods":[18],"for":[19],"training":[20],"deep":[21],"neural":[22],"networks.":[23],"can":[25],"be":[26],"viewed":[27],"as":[28,80,91],"a":[29,40,67,81,92],"two":[30,97],"time-scale":[31],"algorithm,":[32,83],"where":[33],"the":[34,44],"fast":[35],"dynamics":[36,46],"(inner":[37],"optimizer)":[38,48],"determine":[39],"search":[41],"direction":[42],"slow":[45],"(outer":[47],"perform":[49],"updates":[50],"by":[51],"moving":[52],"along":[53],"this":[54],"direction.":[55],"We":[56],"prove":[57],"that,":[58],"with":[59,96],"appropriate":[60],"choice":[61],"step-sizes,":[63],"converges":[65],"stationary":[68],"point":[69],"smooth":[71],"non-convex":[72],"functions.":[73],"Although":[74],"is":[76,86],"described":[77],"implemented":[79],"serial":[82],"our":[84],"analysis":[85],"based":[87],"on":[88],"viewing":[89],"multi-agent":[93],"optimization":[94],"method":[95],"agents":[98],"communicating":[99],"periodically.":[100]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}