{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T02:50:45Z","timestamp":1750301445046,"version":"3.41.0"},"reference-count":52,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T00:00:00Z","timestamp":1687910400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"JSPS KAKENHI","award":["19H04179, 22H01701"],"award-info":[{"award-number":["19H04179, 22H01701"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Evol. Learn. Optim."],"published-print":{"date-parts":[[2023,6,30]]},"abstract":"<jats:p>In this study, we consider a continuous min\u2013max optimization problem min<jats:sub><jats:italic>x<\/jats:italic>\u2208 \ud835\udd4f<\/jats:sub>max<jats:sub><jats:italic>y<\/jats:italic>\u2208 \ud835\udd50<\/jats:sub><jats:italic>f<\/jats:italic>(<jats:italic>x, y<\/jats:italic>) whose objective function is a black-box. We propose a novel approach to minimize the worst-case objective function<jats:italic>F<\/jats:italic>(<jats:italic>x<\/jats:italic>) = max<jats:sub><jats:italic>y<\/jats:italic>\u2208 \ud835\udd50<\/jats:sub><jats:italic>f<\/jats:italic>(<jats:italic>x, y<\/jats:italic>) directly using a covariance matrix adaptation evolution strategy in which the rankings of solution candidates are approximated by our proposed worst-case ranking approximation mechanism. We develop two variants of worst-case ranking approximation combined with a covariance matrix adaptation evolution strategy and approximate gradient ascent as numerical solvers for the inner maximization problem. Numerical experiments show that our proposed approach outperforms several existing approaches when the objective function is a smooth strongly convex\u2013concave function and the interaction between<jats:italic>x<\/jats:italic>and<jats:italic>y<\/jats:italic>is strong. We investigate the advantages of the proposed approach for problems where the objective function is not limited to smooth strongly convex\u2013concave functions. The effectiveness of the proposed approach is demonstrated in the robust berthing control problem with uncertainty.<\/jats:p>","DOI":"10.1145\/3603716","type":"journal-article","created":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T12:29:33Z","timestamp":1686313773000},"page":"1-32","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Covariance Matrix Adaptation Evolutionary Strategy with Worst-Case Ranking Approximation for Min\u2013Max Optimization and Its Application to Berthing Control Tasks"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7729-8496","authenticated-orcid":false,"given":"Atsuhiro","family":"Miyagi","sequence":"first","affiliation":[{"name":"Taisei Corporation and University of Tsukuba, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5314-8848","authenticated-orcid":false,"given":"Yoshiki","family":"Miyauchi","sequence":"additional","affiliation":[{"name":"Osaka University, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2819-1297","authenticated-orcid":false,"given":"Atsuo","family":"Maki","sequence":"additional","affiliation":[{"name":"Osaka University, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3895-219X","authenticated-orcid":false,"given":"Kazuto","family":"Fukuchi","sequence":"additional","affiliation":[{"name":"University of Tsukuba and RIKEN Center for Advanced Intelligence Project, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5015-3812","authenticated-orcid":false,"given":"Jun","family":"Sakuma","sequence":"additional","affiliation":[{"name":"University of Tsukuba and RIKEN Center for Advanced Intelligence Project, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2760-8123","authenticated-orcid":false,"given":"Youhei","family":"Akimoto","sequence":"additional","affiliation":[{"name":"University of Tsukuba and RIKEN Center for Advanced Intelligence Project, Japan"}]}],"member":"320","published-online":{"date-parts":[[2023,6,28]]},"reference":[{"key":"e_1_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512290.3528690"},{"key":"e_1_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1137\/20M1373815"},{"key":"e_1_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1162\/evco_a_00260"},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3520304.3533648"},{"key":"e_1_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510425"},{"key":"e_1_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58112-1_6"},{"key":"e_1_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321709"},{"key":"e_1_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.5089993"},{"key":"e_1_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1830483.1830556"},{"key":"e_1_3_3_11_1","doi-asserted-by":"crossref","unstructured":"H. J. C. Barbosa. 1999. A coevolutionary genetic algorithm for constrained optimization. In Proceedings of the 1999 Congress on Evolutionary Computation (CEC\u201999) Vol. 3. 1605\u20131611.","DOI":"10.1109\/CEC.1999.785466"},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1090.0319"},{"key":"e_1_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1090.0715"},{"key":"e_1_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327345.3327478"},{"key":"e_1_3_3_15_1","volume-title":"Well Placement Optimization","author":"Bouzarkouna Z.","year":"2012","unstructured":"Z. Bouzarkouna. 2012. Well Placement Optimization. Thesis. Universit\u00e9 Paris Sud\u2013Paris XI. https:\/\/tel.archives-ouvertes.fr\/tel-00690456."},{"key":"e_1_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10596-011-9254-2"},{"key":"e_1_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/cnm.2554"},{"key":"e_1_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3406325.3451125"},{"key":"e_1_3_3_19_1","unstructured":"J. Diakonikolas C. Daskalakis and M. Jordan. 2021. Efficient methods for structured nonconvex-nonconcave min-max optimization. In Proceedings of the 24th International Conference on Artificial Intelligence and Statistics Vol. 130. 2746\u20132754. https:\/\/proceedings.mlr.press\/v130\/diakonikolas21a.html."},{"key":"e_1_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.5016090"},{"key":"e_1_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1570256.1570333"},{"key":"e_1_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321842"},{"key":"e_1_3_3_23_1","first-page":"145","volume-title":"Principled Design of Continuous Stochastic Search: From Theory to Practice","author":"Hansen N.","year":"2014","unstructured":"N. Hansen and A. Auger. 2014. Principled Design of Continuous Stochastic Search: From Theory to Practice. Springer, Berlin, Germany, 145\u2013180."},{"key":"e_1_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1830761.1830790"},{"key":"e_1_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1162\/106365601750190398"},{"key":"e_1_3_3_26_1","doi-asserted-by":"crossref","unstructured":"J. W. Herrmann. 1999. A genetic algorithm for minimax optimization problems. In Proceedings of the 1999 Congress on Evolutionary Computation (CEC\u201999) Vol. 2. 1099\u20131103.","DOI":"10.1109\/CEC.1999.782545"},{"key":"e_1_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143997.1144082"},{"key":"e_1_3_3_28_1","volume-title":"Rank Correlation Methods (5th ed.)","author":"Kendall M.","year":"1990","unstructured":"M. Kendall and J. D. Gibbons. 1990. Rank Correlation Methods (5th ed.). Oxford University Press."},{"key":"e_1_3_3_29_1","unstructured":"T. Liang and J. Stokes. 2019. Interaction matters: A note on non-asymptotic local convergence of generative adversarial networks. In Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics Vol. 89. 907\u2013915. https:\/\/proceedings.mlr.press\/v89\/liang19b.html."},{"key":"e_1_3_3_30_1","first-page":"34","article-title":"First-order convergence theory for weakly-convex-weakly-concave min-max problems","volume":"22","author":"Liu M.","year":"2021","unstructured":"M. Liu, H. Rafique, Q. Lin, and T. Yang. 2021. First-order convergence theory for weakly-convex-weakly-concave min-max problems. Journal of Machine Learning Research 22, 1 (Jan. 2021), Article 169, 34 pages.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_3_31_1","unstructured":"S. Liu S. Lu X. Chen Y. Feng K. Xu A. Al-Dujaili M. Hong and U. O\u2019Reilly. 2020. Min-max optimization without gradients: Convergence and applications to black-box evasion and poisoning attacks. In Proceedings of the 37th International Conference on Machine Learning Vol. 119. 6282\u20136293. https:\/\/proceedings.mlr.press\/v119\/liu20j.html."},{"key":"e_1_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00773-019-00642-3"},{"key":"e_1_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:OPTE.0000033376.89159.65"},{"key":"e_1_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321736"},{"key":"e_1_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3449639.3459291"},{"key":"e_1_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109842"},{"key":"e_1_3_3_37_1","doi-asserted-by":"crossref","unstructured":"A. Miyagi H. Yamamoto Y. Akimoto and Z. Xue. 2018. Parallel workflow to optimize well placement in heterogeneous reservoir using covariance matrix adaptation evolution strategy. InProceedings of the 14th Greenhouse Gas Control Technologies Conference (GHGT-14). 10.","DOI":"10.2139\/ssrn.3366345"},{"key":"e_1_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2021.110390"},{"key":"e_1_3_3_39_1","volume-title":"Advances in Neural Information Processing Systems","author":"Nouiehed M.","year":"2019","unstructured":"M. Nouiehed, M. Sanjabi, T. Huang, J. D. Lee, and M. Razaviyayn. 2019. Solving a class of non-convex min-max games using iterative first order methods. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Red Hook, NY, 1\u20139.https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/25048eb6a33209cb5a815bff0cf6887c-Paper.pdf."},{"key":"e_1_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0951-8320(01)00120-X"},{"key":"e_1_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10596-009-9142-1"},{"key":"e_1_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2110.03950"},{"key":"e_1_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3449639.3459358"},{"key":"e_1_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2692963"},{"key":"e_1_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3003851"},{"key":"e_1_3_3_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10898-012-9951-y"},{"key":"e_1_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2018.8632281"},{"key":"e_1_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3449639.3459290"},{"key":"e_1_3_3_49_1","volume-title":"Proceedings of the 10th International Conference on Autonomous Agents and Multiagent Systems (AAMAS\u201911)","author":"Urieli D.","year":"2011","unstructured":"D. Urieli, P. MacAlpine, S. Kalyanakrishnan, Y. Bentor, and P. Stone. 2011. On optimizing interdependent skills: A case study in simulated 3D humanoid robot soccer. In Proceedings of the 10th International Conference on Autonomous Agents and Multiagent Systems (AAMAS\u201911). http:\/\/www.cs.utexas.edu\/users\/ai-lab?AAMAS11-urieli."},{"key":"e_1_3_3_50_1","first-page":"2373","volume-title":"Advances in Neural Information Processing Systems","author":"Vlatakis-Gkaragkounis E. V.","year":"2021","unstructured":"E. V. Vlatakis-Gkaragkounis, L. Flokas, and G. Piliouras. 2021. Solving min-max optimization with hidden structure via gradient descent ascent. In Advances in Neural Information Processing Systems, Vol. 34. Curran Associates, Red Hook, NY, 2373\u20132386. https:\/\/proceedings.neurips.cc\/paper\/2021\/file\/13bf4a96378f3854bcd9792d132eff9f-Paper.pdf."},{"key":"e_1_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1076\/iaij.4.1.5.16466"},{"key":"e_1_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3205651.3205669"},{"key":"e_1_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.2118\/86880-PA"}],"container-title":["ACM Transactions on Evolutionary Learning and Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603716","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3603716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:21Z","timestamp":1750178241000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603716"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,28]]},"references-count":52,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,6,30]]}},"alternative-id":["10.1145\/3603716"],"URL":"https:\/\/doi.org\/10.1145\/3603716","relation":{},"ISSN":["2688-299X","2688-3007"],"issn-type":[{"type":"print","value":"2688-299X"},{"type":"electronic","value":"2688-3007"}],"subject":[],"published":{"date-parts":[[2023,6,28]]},"assertion":[{"value":"2022-08-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-14","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-06-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}