{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:28:56Z","timestamp":1781584136685,"version":"3.54.5"},"reference-count":49,"publisher":"MIT Press","issue":"4","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>When it comes to solving optimization problems with evolutionary algorithms (EAs) in a reliable and scalable manner, detecting and exploiting linkage information, that is, dependencies between variables, can be key. In this paper, we present the latest version of, and propose substantial enhancements to, the gene-pool optimal mixing evolutionary algorithm (GOMEA): an EA explicitly designed to estimate and exploit linkage information. We begin by performing a large-scale search over several GOMEA design choices to understand what matters most and obtain a generally best-performing version of the algorithm. Next, we introduce a novel version of GOMEA, called CGOMEA, where linkage-based variation is further improved by filtering solution mating based on conditional dependencies. We compare our latest version of GOMEA, the newly introduced CGOMEA, and another contending linkage-aware EA, DSMGA-II, in an extensive experimental evaluation, involving a benchmark set of nine black-box problems that can be solved efficiently only if their inherent dependency structure is unveiled and exploited. Finally, in an attempt to make EAs more usable and resilient to parameter choices, we investigate the performance of different automatic population management schemes for GOMEA and CGOMEA, de facto making the EAs parameterless. Our results show that GOMEA and CGOMEA significantly outperform the original GOMEA and DSMGA-II on most problems, setting a new state of the art for the field.<\/jats:p>","DOI":"10.1162\/evco_a_00338","type":"journal-article","created":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T17:58:31Z","timestamp":1688147911000},"page":"371-397","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":7,"title":["Parameterless Gene-Pool Optimal Mixing Evolutionary Algorithms"],"prefix":"10.1162","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0945-0262","authenticated-orcid":true,"given":"Arkadiy","family":"Dushatskiy","sequence":"first","affiliation":[{"name":"Evolutionary Intelligence Group, Centrum Wiskunde and Informatica, Amsterdam, 1098XG, the Netherlands arkadiy.dushatskiy@cwi.nl"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Virgolin","sequence":"additional","affiliation":[{"name":"Evolutionary Intelligence Group, Centrum Wiskunde and Informatica, Amsterdam, 1098XG, the Netherlands marco.virgolin@cwi.nl"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4599-0733","authenticated-orcid":true,"given":"Anton","family":"Bouter","sequence":"additional","affiliation":[{"name":"Evolutionary Intelligence Group, Centrum Wiskunde and Informatica, Amsterdam, 1098XG, the Netherlands anton.bouter@cwi.nl"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9308-5159","authenticated-orcid":true,"given":"Dirk","family":"Thierens","sequence":"additional","affiliation":[{"name":"Department of Information and Computing, Utrecht University, Utrecht, 3584CC, the Netherlands d.thierens@uu.nl"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4186-6666","authenticated-orcid":true,"given":"Peter A. N.","family":"Bosman","sequence":"additional","affiliation":[{"name":"Evolutionary Intelligence Group, Centrum Wiskunde and Informatica, Amsterdam, 1098XG, the Netherlands"},{"name":"Department of Software Technology, Delft University of Technology, Delft, 2628XE, the Netherlands peter.bosman@cwi.nl"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"2024120202545103600_B1","first-page":"38","article-title":"Removing the genetics from the standard genetic algorithm","author":"Baluja","year":"1995","journal-title":"Proceedings of Machine Learning"},{"key":"2024120202545103600_B2","author":"Baluja","year":"1997","journal-title":"Combining multiple optimization runs with optimal dependency trees"},{"key":"2024120202545103600_B3","first-page":"663","article-title":"The roles of local search, model building and optimal mixing in evolutionary algorithms from a BBO perspective","author":"Bosman","year":"2011","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference"},{"key":"2024120202545103600_B4","first-page":"585","article-title":"Linkage neighbors, optimal mixing and forced improvements in genetic algorithms","author":"Bosman","year":"2012","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference"},{"key":"2024120202545103600_B5","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1007\/978-3-642-32937-1_28","article-title":"On measures to build linkage trees in LTGA","author":"Bosman","year":"2012","journal-title":"Proceedings of the International Conference on Parallel Problem Solving from Nature"},{"key":"2024120202545103600_B6","first-page":"359","article-title":"More concise and robust linkage learning by filtering and combining linkage hierarchies","author":"Bosman","year":"2013","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference"},{"issue":"9","key":"2024120202545103600_B7","doi-asserted-by":"publisher","first-page":"3776","DOI":"10.1002\/mp.13681","article-title":"GPU-accelerated bi-objective treatment planning for prostate high-dose-rate brachytherapy","volume":"46","author":"Bouter","year":"2019","journal-title":"Medical Physics"},{"key":"2024120202545103600_B8","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1145\/3512290.3528797","article-title":"GPU-accelerated parallel gene-pool optimal mixing in a gray-box optimization setting","author":"Bouter","year":"2022","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference"},{"key":"2024120202545103600_B9","first-page":"603","article-title":"Leveraging conditional linkage models in gray-box optimization with the real-valued gene-pool optimal mixing evolutionary algorithm","author":"Bouter","year":"2020","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference"},{"key":"2024120202545103600_B10","doi-asserted-by":"crossref","first-page":"745","DOI":"10.1145\/3071178.3071236","article-title":"Two-edge graphical linkage model for DSMGA-II","author":"Chen","year":"2017","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference"},{"key":"2024120202545103600_B11","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1145\/3071178.3071285","article-title":"Optimizing one million variable NK landscapes by hybridizing deterministic recombination and local search","author":"Chicano","year":"2017","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference"},{"key":"2024120202545103600_B12","first-page":"424","article-title":"MIMIC: Finding optima by estimating probability densities","author":"De Bonet","year":"1997","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2024120202545103600_B13","first-page":"93","article-title":"Analyzing deception in trap functions","volume-title":"Foundations of genetic algorithms","author":"Deb","year":"1993"},{"issue":"2","key":"2024120202545103600_B14","first-page":"131","article-title":"Multimodal deceptive functions","volume":"7","author":"Deb","year":"1993","journal-title":"Complex Systems"},{"key":"2024120202545103600_B15","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1007\/978-3-319-45823-6_5","article-title":"The multiple insertion pyramid: A fast parameter-less population scheme","author":"den Besten","year":"2016","journal-title":"Proceedings of the International Conference on Parallel Problem Solving from Nature"},{"issue":"1","key":"2024120202545103600_B16","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.swevo.2011.02.002","article-title":"A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms","volume":"1","author":"Derrac","year":"2011","journal-title":"Swarm and Evolutionary Computation"},{"key":"2024120202545103600_B17","article-title":"Theory of evolutionary computation: Recent developments in discrete optimization","author":"Doerr","year":"2019"},{"issue":"2","key":"2024120202545103600_B18","doi-asserted-by":"publisher","DOI":"10.1145\/3453141","article-title":"A novel approach to designing surrogate-assisted genetic algorithms by combining efficient learning of Walsh coefficients and dependencies","volume":"1","author":"Dushatskiy","year":"2021","journal-title":"ACM Transactions on Evolutionary Learning and Optimization"},{"key":"2024120202545103600_B19","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1145\/3321707.3321760","article-title":"Convolutional neural network surrogate-assisted GOMEA","author":"Dushatskiy","year":"2019","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference"},{"issue":"3","key":"2024120202545103600_B20","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1162\/EVCO_a_00148","article-title":"Fast and efficient black box optimization using the parameter-less population pyramid","volume":"23","author":"Goldman","year":"2015","journal-title":"Evolutionary Computation"},{"issue":"3","key":"2024120202545103600_B21","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1145\/3381343.3381344","article-title":"Human-competitive results awards\u2014\u201cHumies\u201d 2019\u2014announces winners at GECCO","volume":"12","author":"Goodman","year":"2020","journal-title":"SIGEVOlution"},{"key":"2024120202545103600_B22","first-page":"258","article-title":"A parameter-less genetic algorithm","author":"Harik","year":"1999","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference"},{"issue":"4","key":"2024120202545103600_B23","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1109\/4235.797971","article-title":"The compact genetic algorithm","volume":"3","author":"Harik","year":"1999","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"2024120202545103600_B24","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1007\/978-3-540-34954-9_3","article-title":"Linkage learning via probabilistic modeling in the extended compact genetic algorithm (ECGA)","volume-title":"Scalable optimization via probabilistic modeling","author":"Harik","year":"2006"},{"key":"2024120202545103600_B25","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/3-540-32363-5_1","article-title":"Memetic evolutionary algorithms","volume-title":"Recent advances in memetic algorithms","author":"Hart","year":"2005"},{"key":"2024120202545103600_B26","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1090.001.0001","volume-title":"Adaptation in natural and artificial systems: An introductory analysis with applications to biology, control, and artificial intelligence","author":"Holland","year":"1992"},{"key":"2024120202545103600_B27","first-page":"519","article-title":"Optimization by pairwise linkage detection, incremental linkage set, and restricted\/back mixing: DSMGA-II","author":"Hsu","year":"2015","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference"},{"key":"2024120202545103600_B28","doi-asserted-by":"crossref","first-page":"814","DOI":"10.1109\/ICEC.1996.542706","article-title":"The gene expression messy genetic algorithm","author":"Kargupta","year":"1996","journal-title":"Proceedings of the IEEE International Conference on Evolutionary Computation"},{"key":"2024120202545103600_B29","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1007\/978-0-387-84816-7_5","article-title":"MIC: Mutual information based hierarchical clustering","volume-title":"Information theory and statistical learning","author":"Kraskov","year":"2009"},{"key":"2024120202545103600_B30","volume-title":"Estimation of distribution algorithms: A new tool for evolutionary computation","author":"Larra\u00f1aga","year":"2001"},{"key":"2024120202545103600_B31","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1145\/3205455.3205551","article-title":"Investigation of the exponential population scheme for genetic algorithms","author":"Lin","year":"2018","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference"},{"key":"2024120202545103600_B32","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-32494-1","volume-title":"Towards a new evolutionary computation: Advances on estimation of distribution algorithms","author":"Lozano","year":"2006"},{"key":"2024120202545103600_B33","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1016\/j.swevo.2018.02.005","article-title":"Multi-objective gene-pool optimal mixing evolutionary algorithm with the interleaved multi-start scheme","volume":"40","author":"Luong","year":"2018","journal-title":"Swarm and Evolutionary Computation"},{"issue":"4","key":"2024120202545103600_B34","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1162\/evco.1999.7.4.353","article-title":"FDA\u2014A scalable evolutionary algorithm for the optimization of additively decomposed functions","volume":"7","author":"M\u00fchlenbein","year":"1999","journal-title":"Evolutionary Computation"},{"key":"2024120202545103600_B35","first-page":"178","article-title":"From recombination of genes to the estimation of distributions I. binary parameters","author":"M\u00fchlenbein","year":"1996","journal-title":"Proceedings of the International Conference on Parallel Problem Solving from Nature"},{"key":"2024120202545103600_B36","first-page":"104","article-title":"First-improvement vs. best-improvement local optima networks of NK landscapes","author":"Ochoa","year":"2010","journal-title":"Proceedings of the International Conference on Parallel Problem Solving from Nature"},{"key":"2024120202545103600_B37","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/978-3-540-32373-0_6","article-title":"Hierarchical Bayesian optimization algorithm","volume-title":"Hierarchical Bayesian optimization algorithm","author":"Pelikan","year":"2005"},{"key":"2024120202545103600_B38","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1007\/978-3-540-34954-9_4","article-title":"Hierarchical Bayesian optimization algorithm","volume-title":"Scalable optimization via probabilistic modeling","author":"Pelikan","year":"2006"},{"key":"2024120202545103600_B39","first-page":"525","article-title":"BOA: The Bayesian optimization algorithm","volume":"1","author":"Pelikan","year":"1999","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference"},{"key":"2024120202545103600_B40","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1007\/978-1-4471-0819-1_39","article-title":"The bivariate marginal distribution algorithm","volume-title":"Advances in Soft Computing","author":"Pelikan","year":"1999"},{"key":"2024120202545103600_B41","first-page":"851","article-title":"Performance of evolutionary algorithms on NK landscapes with nearest neighbor interactions and tunable overlap","author":"Pelikan","year":"2009","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference"},{"issue":"6","key":"2024120202545103600_B42","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1109\/TEVC.2020.2985497","article-title":"Empirical linkage learning","volume":"24","author":"Przewozniczek","year":"2020","journal-title":"IEEE Transactions on Evolutionary Computation"},{"issue":"4","key":"2024120202545103600_B43","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1162\/evco.1999.7.4.331","article-title":"Scalability problems of simple genetic algorithms","volume":"7","author":"Thierens","year":"1999","journal-title":"Evolutionary Computation"},{"key":"2024120202545103600_B44","first-page":"264","article-title":"The linkage tree genetic algorithm","author":"Thierens","year":"2010","journal-title":"Proceedings of the International Conference on Parallel Problem Solving from Nature, Part I"},{"key":"2024120202545103600_B45","first-page":"617","article-title":"Optimal mixing evolutionary algorithms","author":"Thierens","year":"2011","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference"},{"key":"2024120202545103600_B46","first-page":"293","article-title":"Towards realistic optimization benchmarks: A questionnaire on the properties of real-world problems","author":"van der Blom","year":"2020","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference Companion"},{"key":"2024120202545103600_B47","doi-asserted-by":"crossref","first-page":"1041","DOI":"10.1145\/3071178.3071287","article-title":"Scalable genetic programming by gene-pool optimal mixing and input-space entropy-based building-block learning","author":"Virgolin","year":"2017","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference"},{"issue":"4","key":"2024120202545103600_B48","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.7.4.046501","article-title":"Machine learning for the prediction of pseudorealistic pediatric abdominal phantoms for radiation dose reconstruction","volume":"7","author":"Virgolin","year":"2020","journal-title":"Journal of Medical Imaging"},{"issue":"1","key":"2024120202545103600_B49","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1109\/4235.585893","article-title":"No free lunch theorems for optimization","volume":"1","author":"Wolpert","year":"1997","journal-title":"IEEE Transactions on Evolutionary Computation"}],"container-title":["Evolutionary Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/evco\/article-pdf\/32\/4\/371\/2477804\/evco_a_00338.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/evco\/article-pdf\/32\/4\/371\/2477804\/evco_a_00338.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T02:55:13Z","timestamp":1733108113000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/evco\/article\/32\/4\/371\/116609\/Parameterless-Gene-Pool-Optimal-Mixing"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":49,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,12,2]]},"published-print":{"date-parts":[[2024,12,2]]}},"URL":"https:\/\/doi.org\/10.1162\/evco_a_00338","relation":{},"ISSN":["1530-9304"],"issn-type":[{"value":"1530-9304","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024]]},"published":{"date-parts":[[2024]]}}}