{"id":"https://openalex.org/W4385213390","doi":"https://doi.org/10.1145/3583133.3597059","title":"Lottery tickets in evolutionary optimization: On sparse backpropagation-free trainability","display_name":"Lottery tickets in evolutionary optimization: On sparse backpropagation-free trainability","publication_year":2023,"publication_date":"2023-07-15","ids":{"openalex":"https://openalex.org/W4385213390","doi":"https://doi.org/10.1145/3583133.3597059"},"language":"en","primary_location":{"id":"doi:10.1145/3583133.3597059","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583133.3597059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","raw_type":"proceedings-article"},"type":"conference-paper","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/A5013857977","display_name":"Robert Tjarko Lange","orcid":"https://orcid.org/0009-0005-8799-1138"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Robert Lange","raw_affiliation_strings":["Technical Univ. Berlin, Berlin, Germany"],"raw_orcid":"https://orcid.org/0009-0005-8799-1138","affiliations":[{"raw_affiliation_string":"Technical Univ. Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015039578","display_name":"Henning Sprekeler","orcid":"https://orcid.org/0000-0003-0690-3553"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Henning Sprekeler","raw_affiliation_strings":["Technical Univ. Berlin, Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0690-3553","affiliations":[{"raw_affiliation_string":"Technical Univ. Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":0.4113,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55855812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"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/T12676","display_name":"Machine Learning and ELM","score":0.9832000136375427,"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/T12676","display_name":"Machine Learning and ELM","score":0.9832000136375427,"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/T10320","display_name":"Neural Networks and Applications","score":0.9821000099182129,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9782000184059143,"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":0.6055227518081665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5507987141609192},{"id":"https://openalex.org/keywords/local-optimum","display_name":"Local optimum","score":0.5388280153274536},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4943978786468506},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.46856218576431274},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.45506545901298523},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.4320530891418457},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41574689745903015},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3859804570674896},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24341759085655212}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6055227518081665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5507987141609192},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.5388280153274536},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4943978786468506},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.46856218576431274},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.45506545901298523},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4320530891418457},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41574689745903015},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3859804570674896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24341759085655212},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583133.3597059","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583133.3597059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2894173309","https://openalex.org/W2115605526","https://openalex.org/W4387932263","https://openalex.org/W2098962763","https://openalex.org/W3093883775","https://openalex.org/W1539246760","https://openalex.org/W2786746258","https://openalex.org/W2371065793","https://openalex.org/W2157746493","https://openalex.org/W1977222966"],"abstract_inverted_index":{"Lottery":[0],"tickets":[1],"in":[2],"Deep":[3],"Learning":[4],"[2]":[5],"refer":[6],"to":[7,15,57,81,170],"highly":[8,68,115],"sparse":[9,27,69,85,116],"neural":[10],"network":[11,107,124],"initializations,":[12],"which":[13,96,141],"train":[14],"the":[16,43,65,106,112,156,161,198],"performance":[17],"level":[18],"of":[19,25,37,49,67,114,123],"their":[20],"dense":[21],"counterparts":[22],"The":[23,192],"existence":[24,66,113],"such":[26],"trainable":[28,70],"initializations":[29,71,118,136],"has":[30],"previously":[31],"been":[32],"documented":[33],"for":[34,72,119],"a":[35,89,120],"variety":[36],"gradient-based":[38],"training":[39],"settings.":[40,130],"But":[41],"is":[42],"lottery":[44],"ticket":[45],"phenomenon":[46],"an":[47,138],"idiosyncrasy":[48],"stochastic":[50],"gradient":[51,82],"descent":[52,83],"or":[53],"does":[54],"it":[55],"generalize":[56],"evolutionary":[58],"optimization?":[59],"In":[60,168],"this":[61],"paper":[62,194],"we":[63,132,154],"establish":[64],"evolution":[73,126,145],"strategies":[74,127],"(ES)":[75],"and":[76,100,128,149,165,175,179,189],"characterize":[77],"qualitative":[78],"differences":[79],"compared":[80],"(GD)-based":[84],"training.":[86,152],"We":[87,110],"introduce":[88],"novel":[90],"signal-to-noise":[91],"(SNR)":[92],"iterative":[93],"pruning":[94,108],"procedure,":[95],"extracts":[97],"evolvable":[98,117],"sub-networks":[99],"incorporates":[101],"loss":[102],"curvature":[103],"information":[104],"into":[105],"step.":[109],"demonstrate":[111],"wide":[121],"range":[122],"architectures,":[125],"task":[129],"Furthermore,":[131],"find":[133],"that":[134],"these":[135],"encode":[137],"inductive":[139],"bias,":[140],"transfers":[142],"across":[143,186],"different":[144,162],"strategies,":[146],"related":[147],"tasks":[148],"even":[150],"GD-based":[151],"Finally,":[153],"compare":[155],"local":[157,177],"optima":[158,178],"resulting":[159],"from":[160],"optimization":[163],"paradigms":[164],"sparsity":[166,187],"levels.":[167],"contrast":[169],"GD,":[171],"ES":[172],"explore":[173],"diverse":[174],"flat":[176],"do":[180],"not":[181],"preserve":[182],"linear":[183],"mode":[184],"connectivity":[185],"levels":[188],"independent":[190],"runs.":[191],"full":[193],"was":[195],"accepted":[196],"at":[197],"ICML":[199],"conference":[200],"[4].":[201]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}