{"id":"https://openalex.org/W4384024384","doi":"https://doi.org/10.1145/3583131.3590368","title":"Mini-Batching, Gradient-Clipping, First- versus Second-Order: What Works in Gradient-Based Coefficient Optimisation for Symbolic Regression?","display_name":"Mini-Batching, Gradient-Clipping, First- versus Second-Order: What Works in Gradient-Based Coefficient Optimisation for Symbolic Regression?","publication_year":2023,"publication_date":"2023-07-12","ids":{"openalex":"https://openalex.org/W4384024384","doi":"https://doi.org/10.1145/3583131.3590368"},"language":"en","primary_location":{"id":"doi:10.1145/3583131.3590368","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3583131.3590368","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583131.3590368?download=true","source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3583131.3590368?download=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040011467","display_name":"Joe Harrison","orcid":"https://orcid.org/0000-0002-3427-5251"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832","https://openalex.org/I4405262988"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Joe Harrison","raw_affiliation_strings":["Centrum Wiskunde & Informatica (CWI), Amsterdam, Netherlands","Delft University of Technology, Amsterdam, Netherlands","Centrum Wiskunde & Informatica (CWI), Amsterdam, Netherlands Delft University of Technology, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-3427-5251","affiliations":[{"raw_affiliation_string":"Centrum Wiskunde & Informatica (CWI), Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1341640284"]},{"raw_affiliation_string":"Delft University of Technology, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Centrum Wiskunde & Informatica (CWI), Amsterdam, Netherlands Delft University of Technology, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1341640284","https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014995636","display_name":"Marco Virgolin","orcid":"https://orcid.org/0000-0001-8905-9313"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832","https://openalex.org/I4405262988"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marco Virgolin","raw_affiliation_strings":["Centrum Wiskunde & Informatica (CWI), Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-8905-9313","affiliations":[{"raw_affiliation_string":"Centrum Wiskunde & Informatica (CWI), Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025122230","display_name":"Tanja Alderliesten","orcid":"https://orcid.org/0000-0003-4261-7511"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Tanja Alderliesten","raw_affiliation_strings":["Leiden University, Leiden, Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-4261-7511","affiliations":[{"raw_affiliation_string":"Leiden University, Leiden, Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031539135","display_name":"Peter A. N. Bosman","orcid":"https://orcid.org/0000-0002-4186-6666"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832","https://openalex.org/I4405262988"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Peter Bosman","raw_affiliation_strings":["Centrum Wiskunde & Informatica (CWI), Amsterdam, Netherlands","Delft University of Technology, Amsterdam, Netherlands","Centrum Wiskunde & Informatica (CWI), Amsterdam, Netherlands Delft University of Technology, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-4186-6666","affiliations":[{"raw_affiliation_string":"Centrum Wiskunde & Informatica (CWI), Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1341640284"]},{"raw_affiliation_string":"Delft University of Technology, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Centrum Wiskunde & Informatica (CWI), Amsterdam, Netherlands Delft University of Technology, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1341640284","https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0889,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78797697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"33","issue":null,"first_page":"1127","last_page":"1136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":1.0,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":1.0,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9987999796867371,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9879999756813049,"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/symbolic-regression","display_name":"Symbolic regression","score":0.6983920931816101},{"id":"https://openalex.org/keywords/clipping","display_name":"Clipping (morphology)","score":0.6795650720596313},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6227896213531494},{"id":"https://openalex.org/keywords/genetic-programming","display_name":"Genetic programming","score":0.6196063756942749},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5512545704841614},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5010600090026855},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4823733866214752},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4816788136959076},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47288790345191956},{"id":"https://openalex.org/keywords/genetic-algorithm","display_name":"Genetic algorithm","score":0.46116796135902405},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.45536038279533386},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4405783414840698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41964098811149597},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3814988136291504},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2988125681877136},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29064908623695374},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10048779845237732}],"concepts":[{"id":"https://openalex.org/C2776400721","wikidata":"https://www.wikidata.org/wiki/Q18171762","display_name":"Symbolic regression","level":3,"score":0.6983920931816101},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.6795650720596313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6227896213531494},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.6196063756942749},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5512545704841614},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5010600090026855},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4823733866214752},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4816788136959076},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47288790345191956},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.46116796135902405},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.45536038279533386},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4405783414840698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41964098811149597},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3814988136291504},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2988125681877136},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29064908623695374},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10048779845237732},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3583131.3590368","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3583131.3590368","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583131.3590368?download=true","source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:cwi.nl:33310","is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/33310","pdf_url":"https://ir.cwi.nl/pub/33310/33310.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:tudelft.nl:uuid:02197e3e-2cd1-4d98-a152-c6d28d4264f8","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:02197e3e-2cd1-4d98-a152-c6d28d4264f8","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":{"id":"doi:10.1145/3583131.3590368","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3583131.3590368","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583131.3590368?download=true","source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6729541864","display_name":"EXAMINE \u2013 Evolutionary eXplainable Artificial Medical INtelligence Engine","funder_award_id":"OCENW.KLEIN.111","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384024384.pdf","grobid_xml":"https://content.openalex.org/works/W4384024384.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W158805453","https://openalex.org/W1486968485","https://openalex.org/W1519072852","https://openalex.org/W1529146523","https://openalex.org/W1576818901","https://openalex.org/W1999927946","https://openalex.org/W2058727381","https://openalex.org/W2087070363","https://openalex.org/W2097619956","https://openalex.org/W2194775991","https://openalex.org/W2562182651","https://openalex.org/W2729598826","https://openalex.org/W2782083374","https://openalex.org/W2885530784","https://openalex.org/W2900342595","https://openalex.org/W2963672746","https://openalex.org/W2991933648","https://openalex.org/W3003257820","https://openalex.org/W3004042307","https://openalex.org/W3021291678","https://openalex.org/W3036548566","https://openalex.org/W3038771732","https://openalex.org/W3040225824","https://openalex.org/W3040682934","https://openalex.org/W3046457509","https://openalex.org/W3099281365","https://openalex.org/W3209828932","https://openalex.org/W4226083102","https://openalex.org/W4285805355","https://openalex.org/W4293775970"],"related_works":["https://openalex.org/W2968285896","https://openalex.org/W2381504162","https://openalex.org/W1567571923","https://openalex.org/W2472646430","https://openalex.org/W2610450612","https://openalex.org/W2549153708","https://openalex.org/W2897801744","https://openalex.org/W2147355282","https://openalex.org/W2394133867","https://openalex.org/W1662819506"],"abstract_inverted_index":{"The":[0,15,177],"aim":[1],"of":[2,17,94,168,179,185],"Symbolic":[3],"Regression":[4],"(SR)":[5],"is":[6,43,135,189],"to":[7,33,78,109,173,194],"discover":[8],"interpretable":[9],"expressions":[10],"that":[11,101,147],"accurately":[12],"describe":[13],"data.":[14],"accuracy":[16],"an":[18],"expression":[19],"depends":[20],"on":[21],"both":[22],"its":[23],"structure":[24,30,186],"and":[25,103,187],"coefficients.":[26],"To":[27],"keep":[28],"the":[29,165,183],"simple":[31],"enough":[32],"be":[34,57,106],"interpretable,":[35],"effective":[36,45],"coefficient":[37,151],"optimisation":[38,42,70,126,149,170,184],"becomes":[39],"key.":[40],"Gradient-based":[41],"clearly":[44],"at":[46],"training":[47],"neural":[48],"networks":[49],"in":[50,63,75,127,141,157],"Deep":[51],"Learning":[52],"(DL),":[53],"which":[54],"can":[55,105],"essentially":[56],"viewed":[58],"as":[59,72],"large,":[60],"over-parameterised":[61],"expressions:":[62],"this":[64],"paper,":[65],"we":[66,82,121,145],"study":[67],"how":[68],"gradient-based":[69,125],"techniques":[71,86],"often":[73],"used":[74],"DL":[76],"transfer":[77],"SR.":[79],"In":[80],"particular,":[81],"first":[83],"assess":[84],"what":[85],"work":[87],"well":[88],"across":[89],"random":[90],"SR":[91,97,133],"expressions,":[92],"independent":[93],"any":[95],"specific":[96],"algorithm.":[98],"We":[99],"find":[100,146],"mini-batching":[102],"gradient-clipping":[104],"helpful":[107],"(similar":[108],"DL),":[110],"while":[111],"second-order":[112,148,169],"optimisers":[113],"outperform":[114],"first-order":[115],"ones":[116],"(different":[117],"from":[118],"DL).":[119],"Next,":[120],"consider":[122],"whether":[123],"including":[124],"Genetic":[128],"Programming":[129],"(GP),":[130],"a":[131,142,191],"classic":[132],"algorithm,":[134],"beneficial.":[136],"On":[137],"five":[138],"real-world":[139],"datasets,":[140],"generation-based":[143],"comparison,":[144],"outperforms":[150],"mutation":[152],"(or":[153],"no":[154],"optimisation).":[155],"However,":[156],"time-based":[158],"comparisons,":[159],"performance":[160],"gaps":[161],"shrink":[162],"substantially":[163],"because":[164],"computational":[166,180],"expensiveness":[167],"causes":[171],"GP":[172],"perform":[174],"fewer":[175],"generations.":[176],"interplay":[178],"costs":[181],"between":[182],"coefficients":[188],"thus":[190],"critical":[192],"aspect":[193],"consider.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}