{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T05:58:41Z","timestamp":1768456721426,"version":"3.49.0"},"reference-count":51,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2022,3,31]],"date-time":"2022-03-31T00:00:00Z","timestamp":1648684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"JSPS KAKENHI","award":["19H04179 and 19K04858"],"award-info":[{"award-number":["19H04179 and 19K04858"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Evol. Learn. Optim."],"published-print":{"date-parts":[[2022,3,31]]},"abstract":"<jats:p>We propose an approach to saddle point optimization relying only on oracles that solve minimization problems approximately. We analyze its convergence property on a strongly convex\u2013concave problem and show its linear convergence toward the global min\u2013max saddle point. Based on the convergence analysis, we develop a heuristic approach to adapt the learning rate. An implementation of the developed approach using the (1+1)-CMA-ES as the minimization oracle, namely, Adversarial-CMA-ES, is shown to outperform several existing approaches on test problems. Numerical evaluation confirms the tightness of the theoretical convergence rate bound as well as the efficiency of the learning rate adaptation mechanism. As an example of real-world problems, the suggested optimization method is applied to automatic berthing control problems under model uncertainties, showing its usefulness in obtaining solutions robust to uncertainty.<\/jats:p>","DOI":"10.1145\/3510425","type":"journal-article","created":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T22:24:29Z","timestamp":1643840669000},"page":"1-32","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Saddle Point Optimization with Approximate Minimization Oracle and Its Application to Robust Berthing Control"],"prefix":"10.1145","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2760-8123","authenticated-orcid":false,"given":"Youhei","family":"Akimoto","sequence":"first","affiliation":[{"name":"Faculty of Engineering, Information and Systems, University of Tsukuba &amp; RIKEN Center for Advanced Intelligence Project, Tsukuba, Ibaraki, Japan"}]},{"given":"Yoshiki","family":"Miyauchi","sequence":"additional","affiliation":[{"name":"Department of Naval Architecture and Ocean Engineering, Graduate School of Engineering, Osaka University, Yamadaoka, Suita, Osaka, Japan"}]},{"given":"Atsuo","family":"Maki","sequence":"additional","affiliation":[{"name":"Department of Naval Architecture and Ocean Engineering, Graduate School of Engineering, Osaka University, Yamadaoka, Suita, Osaka, Japan"}]}],"member":"320","published-online":{"date-parts":[[2022,4,5]]},"reference":[{"key":"e_1_3_4_2_1","first-page":"283","volume-title":"Transactions of Society of Naval Architects and Marine Engineers 88","author":"Abkowitz Martin A.","year":"1980","unstructured":"Martin A. Abkowitz. 1980. Measurement of hydrodynamic characteristics from ship maneuvering trials by system identification. In Transactions of Society of Naval Architects and Marine Engineers 88. 283\u2013318."},{"key":"e_1_3_4_3_1","first-page":"486","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","author":"Adolphs Leonard","year":"2019","unstructured":"Leonard Adolphs, Hadi Daneshmand, Aurelien Lucchi, and Thomas Hofmann. 2019. Local saddle point optimization: A curvature exploitation approach. In Proceedings of the International Conference on Artificial Intelligence and Statistics. 486\u2013495."},{"key":"e_1_3_4_4_1","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1145\/3449639.3459266","volume-title":"Proceedings of the Genetic and Evolutionary Computation Conference (GECCO\u201921)","author":"Akimoto Youhei","year":"2021","unstructured":"Youhei Akimoto. 2021. Saddle point optimization with approximate minimization oracle. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO\u201921). 493\u2013501."},{"key":"e_1_3_4_5_1","doi-asserted-by":"publisher","DOI":"10.1162\/evco_a_00260"},{"key":"e_1_3_4_6_1","first-page":"20","volume-title":"Proceedings of the AIP Conference","volume":"2070","author":"Al-Dujaili Abdullah","year":"2019","unstructured":"Abdullah Al-Dujaili, Shashank Srikant, Erik Hemberg, and Una-May O\u2019Reilly. 2019. On the application of danskin\u2019s theorem to derivative-free minimax problems. In Proceedings of the AIP Conference, Vol. 2070. 20\u201326."},{"key":"e_1_3_4_7_1","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.oceaneng.2012.05.001","article-title":"Estimating maneuvering coefficients using system identification methods with experimental, system-based, and CFD free-running trial data","volume":"51","author":"Araki Motoki","year":"2012","unstructured":"Motoki Araki, Hamid Sadat-Hosseini, Yugo Sanada, Kenji Tanimoto, Naoya Umeda, and Frederick Stern. 2012. Estimating maneuvering coefficients using system identification methods with experimental, system-based, and CFD free-running trial data. Ocean Eng. 51 (2012), 63\u201384.","journal-title":"Ocean Eng."},{"key":"e_1_3_4_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1830483.1830556"},{"key":"e_1_3_4_9_1","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1090.0319"},{"key":"e_1_3_4_10_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1090.0715"},{"key":"e_1_3_4_11_1","first-page":"5760","volume-title":"Advances in Neural Information Processing Systems","author":"Bogunovic Ilija","year":"2018","unstructured":"Ilija Bogunovic, Jonathan Scarlett, Stefanie Jegelka, and Volkan Cevher. 2018. Adversarially robust optimization with gaussian processes. In Advances in Neural Information Processing Systems. MIT Press, 5760\u20135770."},{"key":"e_1_3_4_12_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"e_1_3_4_13_1","first-page":"144","volume-title":"Proceedings of the International Conference on Parallel Problem Solving from Nature","author":"Branke J\u00fcrgen","year":"2008","unstructured":"J\u00fcrgen Branke and Johanna Rosenbusch. 2008. New approaches to coevolutionary worst-case optimization. In Proceedings of the International Conference on Parallel Problem Solving from Nature. 144\u2013153."},{"key":"e_1_3_4_14_1","doi-asserted-by":"publisher","DOI":"10.1137\/15M1026924"},{"key":"e_1_3_4_15_1","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2010.547579"},{"key":"e_1_3_4_16_1","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Daskalakis Constantinos","year":"2018","unstructured":"Constantinos Daskalakis, Andrew Ilyas, Vasilis Syrgkanis, and Haoyang Zeng. 2018. Training GANs with optimism. In Proceedings of the International Conference on Learning Representations."},{"issue":"1","key":"e_1_3_4_17_1","doi-asserted-by":"crossref","first-page":"207","DOI":"10.14321\/realanalexch.39.1.0207","article-title":"The implicit and inverse function theorems: Easy proofs","volume":"39","author":"Oliveira Oswaldo de","year":"2013","unstructured":"Oswaldo de Oliveira. 2013. The implicit and inverse function theorems: Easy proofs. Real Anal. Exchange 39, 1 (2013), 207\u2013218.","journal-title":"Real Anal. Exchange"},{"key":"e_1_3_4_18_1","volume-title":"Proceedings of the International Symposium on Systems Engineering and Analysis","author":"Devroye Luc","year":"1972","unstructured":"Luc Devroye. 1972. The compound random search. In Proceedings of the International Symposium on Systems Engineering and Analysis. 195\u2013110."},{"key":"e_1_3_4_19_1","article-title":"A tutorial on bayesian optimization","author":"Frazier Peter I.","year":"2018","unstructured":"Peter I. Frazier. 2018. A tutorial on bayesian optimization. Retrieved from https:\/\/arXiv:1807.02811.","journal-title":"Retrieved from https:\/\/arXiv:1807.02811"},{"key":"e_1_3_4_20_1","doi-asserted-by":"crossref","first-page":"77","DOI":"10.2534\/jjasnaoe1968.1998.77","article-title":"Estimation of wind forces and moments acting on ships","volume":"1998","author":"Fujiwara Toshifumi","year":"1998","unstructured":"Toshifumi Fujiwara, Michio Ueno, and Tadashi Nimura. 1998. Estimation of wind forces and moments acting on ships. J. Soc. Naval Arch. Japan 1998 (1998), 77\u201390. Issue 183.","journal-title":"J. Soc. Naval Arch. Japan"},{"key":"e_1_3_4_21_1","first-page":"362","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","author":"Gidel Gauthier","year":"2017","unstructured":"Gauthier Gidel, Tony Jebara, and Simon Lacoste-Julien. 2017. Frank-wolfe algorithms for saddle point problems. In Proceedings of the International Conference on Artificial Intelligence and Statistics. 362\u2013371."},{"key":"e_1_3_4_22_1","first-page":"2672","volume-title":"Advances in Neural Information Processing Systems","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in Neural Information Processing Systems. MIT Press, 2672\u20132680."},{"key":"e_1_3_4_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33206-7_8"},{"key":"e_1_3_4_24_1","doi-asserted-by":"publisher","DOI":"10.1162\/106365603321828970"},{"key":"e_1_3_4_25_1","doi-asserted-by":"publisher","DOI":"10.1162\/106365601750190398"},{"key":"e_1_3_4_26_1","first-page":"369","volume-title":"A New Look at Solving Minimax Problems with Coevolutionary Genetic Algorithms","author":"Jensen Mikkel T.","year":"2004","unstructured":"Mikkel T. Jensen. 2004. A New Look at Solving Minimax Problems with Coevolutionary Genetic Algorithms. Kluwer Academic Publishers, 369\u2013384."},{"key":"e_1_3_4_27_1","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1007\/978-3-319-46128-1_50","volume-title":"Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases","author":"Karimi Hamed","year":"2016","unstructured":"Hamed Karimi, Julie Nutini, and Mark Schmidt. 2016. Linear convergence of gradient and proximal-gradient methods under the Polyak-\u0141ojasiewicz condition. In Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases. 795\u2013811."},{"key":"e_1_3_4_28_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:NACO.0000023416.59689.4e"},{"key":"e_1_3_4_29_1","volume-title":"A Software Package for Sequential Quadratic Programming","author":"Kraft Dieter","year":"1988","unstructured":"Dieter Kraft. 1988. A Software Package for Sequential Quadratic Programming. Technical Report. DFVLR-FB 88-28, DLR German Aerospace Center\u2014Institute for Flight Mechanics, Koln, Germany."},{"key":"e_1_3_4_30_1","first-page":"907","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","author":"Liang Tengyuan","year":"2019","unstructured":"Tengyuan Liang and James Stokes. 2019. Interaction matters: A note on non-asymptotic local convergence of generative adversarial networks. In Proceedings of the International Conference on Artificial Intelligence and Statistics. 907\u2013915."},{"key":"e_1_3_4_31_1","first-page":"2307","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Liu Sijia","year":"2020","unstructured":"Sijia Liu, Songtao Lu, Xiangyi Chen, Yao Feng, Kaidi Xu, Abdullah Al-Dujaili, Mingyi Hong, and Una-May O\u2019Reilly. 2020. Min-max optimization without gradients: Convergence and applications to black-box evasion and poisoning attacks. In Proceedings of the International Conference on Machine Learning. 2307\u20132318."},{"key":"e_1_3_4_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00773-020-00774-x"},{"key":"e_1_3_4_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00773-019-00642-3"},{"key":"e_1_3_4_34_1","first-page":"1823","volume-title":"Advances in Neural Information Processing Systems","author":"Mescheder Lars","year":"2017","unstructured":"Lars Mescheder, Sebastian Nowozin, and Andreas Geiger. 2017. The numerics of GANs. In Advances in Neural Information Processing Systems. MIT Press, 1823\u20131833."},{"key":"e_1_3_4_35_1","unstructured":"Transport Ministry of Land Infrastructure and Tourism. 2020. White paper on land infrastructure transport and tourism in Japan. Retrieved from https:\/\/www.mlit.go.jp\/en\/statistics\/white-paper-mlit-index.html."},{"key":"e_1_3_4_36_1","article-title":"System parameter exploration of ship maneuvering model for automatic docking \/ berthing using CMA-ES","author":"Miyauchi Yoshiki","year":"2021","unstructured":"Yoshiki Miyauchi, Atsuo Maki, Naoya Umeda, Dimas M. Rachman, and Youhei Akimoto. 2021. System parameter exploration of ship maneuvering model for automatic docking \/ berthing using CMA-ES. Retrieved from https:\/\/arXiv:2111.06124.","journal-title":"Retrieved from https:\/\/arXiv:2111.06124"},{"key":"e_1_3_4_37_1","doi-asserted-by":"crossref","unstructured":"Yoshiki Miyauchi Ryohei Sawada Youhei Akimoto Naoya Umeda and Atsuo Maki. 2022. Optimization on planning of trajectory and control of autonomous berthing and unberthing for the realistic port geometry. Ocean Engineering 245 (2022) 110390.","DOI":"10.1016\/j.oceaneng.2021.110390"},{"key":"e_1_3_4_38_1","first-page":"13","volume-title":"Foundations of Genetic Algorithms","author":"Morinaga Daiki","year":"2019","unstructured":"Daiki Morinaga and Youhei Akimoto. 2019. Generalized drift analysis in continuous domain: Linear convergence of (1+1)-ES on strongly convex functions with lipschitz continuous gradients. In Foundations of Genetic Algorithms. 13\u201324."},{"key":"e_1_3_4_39_1","doi-asserted-by":"crossref","first-page":"1169","DOI":"10.1145\/3449639.3459289","volume-title":"Proceedings of the Genetic and Evolutionary Computation Conference (GECCO\u201921)","author":"Morinaga Daiki","year":"2021","unstructured":"Daiki Morinaga, Kazuto Fukuchi, Jun Sakuma, and Youhei Akimoto. 2021. Convergence rate of the (1+1)-evolution strategy with success-based step-size adaptation on convex quadratic function. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO\u201921). 1169\u20131177."},{"key":"e_1_3_4_40_1","first-page":"5591","volume-title":"Advances in Neural Information Processing Systems","author":"Nagarajan Vaishnavh","year":"2017","unstructured":"Vaishnavh Nagarajan and J. Zico Kolter. 2017. Gradient descent GAN optimization is locally stable. In Advances in Neural Information Processing Systems. MIT Press, 5591\u20135600."},{"key":"e_1_3_4_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"key":"e_1_3_4_42_1","first-page":"14934","volume-title":"Advances in Neural Information Processing Systems","author":"Nouiehed Maher","year":"2019","unstructured":"Maher Nouiehed, Maziar Sanjabi, Tianjian Huang, Jason D Lee, and Meisam Razaviyayn. 2019. Solving a class of non-convex min-max games using iterative first order methods. In Advances in Neural Information Processing Systems. MIT Press, 14934\u201314942."},{"key":"e_1_3_4_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10898-018-0688-0"},{"key":"e_1_3_4_44_1","first-page":"2817","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Pinto Lerrel","year":"2017","unstructured":"Lerrel Pinto, James Davidson, Rahul Sukthankar, and Abhinav Gupta. 2017. Robust adversarial reinforcement learning. In Proceedings of the International Conference on Machine Learning. 2817\u20132826."},{"key":"e_1_3_4_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2692963"},{"key":"e_1_3_4_46_1","volume-title":"Evolutionsstrategie: Optimierung Technisher Systeme nach Prinzipien Der Biologischen Evolution","author":"Rechenberg Ingo","year":"1973","unstructured":"Ingo Rechenberg. 1973. Evolutionsstrategie: Optimierung Technisher Systeme nach Prinzipien Der Biologischen Evolution. Frommann-Holzboog."},{"key":"e_1_3_4_47_1","first-page":"2234","volume-title":"Advances in Neural Information Processing Systems","author":"Salimans Tim","year":"2016","unstructured":"Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, Xi Chen, and Xi Chen. 2016. Improved techniques for training GANs. In Advances in Neural Information Processing Systems. MIT Press, 2234\u20132242."},{"key":"e_1_3_4_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1968.1098903"},{"key":"e_1_3_4_49_1","volume-title":"Proceedings of the International Conference on Learning Representations, Workshop Track","author":"Shioya Hiroaki","year":"2018","unstructured":"Hiroaki Shioya, Yusuke Iwasawa, and Yutaka Matsuo. 2018. Extending robust adversarial reinforcement learning considering adaptation and diversity. In Proceedings of the International Conference on Learning Representations, Workshop Track."},{"key":"e_1_3_4_50_1","doi-asserted-by":"crossref","unstructured":"Kouki Wakita Atsuo Maki Naoya Umeda Yoshiki Miyauchi Tohga Shimoji Dimas M. Rachman and Youhei Akimoto. 2022. On neural network identification for low-speed ship maneuvering model. Journal of Marine Science of Technology (2022).","DOI":"10.1007\/s00773-021-00867-1"},{"key":"e_1_3_4_51_1","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Yadav Abhay","year":"2018","unstructured":"Abhay Yadav, Sohil Shah, Zheng Xu, David Jacobs, and Tom Goldstein. 2018. Stabilizing adversarial nets with prediction methods. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_4_52_1","first-page":"1","volume-title":"Proceedings of the IEEE Congress on Evolutionary Computation","author":"Zhou Aimin","year":"2010","unstructured":"Aimin Zhou and Qingfu Zhang. 2010. A surrogate-assisted evolutionary algorithm for minimax optimization. In Proceedings of the IEEE Congress on Evolutionary Computation. 1\u20137."}],"container-title":["ACM Transactions on Evolutionary Learning and Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3510425","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3510425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:09:45Z","timestamp":1750183785000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3510425"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,31]]},"references-count":51,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,3,31]]}},"alternative-id":["10.1145\/3510425"],"URL":"https:\/\/doi.org\/10.1145\/3510425","relation":{},"ISSN":["2688-299X","2688-3007"],"issn-type":[{"value":"2688-299X","type":"print"},{"value":"2688-3007","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,31]]},"assertion":[{"value":"2021-05-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-01-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-04-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}