{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T20:27:12Z","timestamp":1791491232798,"version":"4.3.4"},"reference-count":75,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"3","funder":[{"DOI":"10.13039\/501100000288","name":"Royal Society","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000288","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003787","name":"Natural Science Foundation of Hebei Province","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"crossref"}]},{"name":"2024 PIMS-Europe Fellowship"},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Control Optim."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>Abstract.<\/jats:p>\n                  <jats:p>We propose a zero-order optimization method for sequential min-max problems that employs two populations of interacting particles. The systems are coupled so that one population aims to solve the inner maximization problem, while the other aims to solve the outer minimization problem. The dynamics are characterized by a consensus-type interaction with additional stochasticity to promote exploration of the landscape of the objective function. Without relying on convexity or concavity assumptions, we establish theoretical convergence guarantees of the algorithm via a suitable mean-field approximation of the particle systems. Numerical experiments illustrate the validity of the proposed approach. In particular, the algorithm is able to identify a global min-max solution, in contrast to gradient-based methods, which typically converge to possibly suboptimal stationary points.<\/jats:p>","DOI":"10.1137\/25m1766760","type":"journal-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T08:01:48Z","timestamp":1779868908000},"page":"1573-1601","source":"Crossref","is-referenced-by-count":2,"title":["A Particle Consensus Approach to Solving Nonconvex-Nonconcave Min-Max Problems"],"prefix":"10.1137","volume":"64","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2478-807X","authenticated-orcid":true,"given":"Giacomo","family":"Borghi","sequence":"first","affiliation":[{"name":"Maxwell Institute for Mathematical Sciences and Department of Mathematics, Heriot\u2013Watt University, Edinburgh, United Kingdom."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4171-0530","authenticated-orcid":true,"given":"Hui","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Mathematics, Hunan University, 2 Lushan S Rd, Changsha, 410008 China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8610-6786","authenticated-orcid":true,"given":"Jinniao","family":"Qiu","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Statistics, University of Calgary, 2500 University Dr NW, Calgary, AB T2N 1N4, Canada."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2026,5,27]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2021.126726"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511559402"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/937503.937505"},{"key":"ref4","doi-asserted-by":"crossref","unstructured":"G. Borghi, M. Herty, and L. Pareschi, A consensus-based algorithm for multi-objective optimization and its mean-field description, in 2022 IEEE 61st Conference on Decision and Control (CDC), IEEE, Piscataway, NJ, 2022, pp. 4131\u20134136.","DOI":"10.1109\/CDC51059.2022.9993095"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s00245-023-10036-y"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1137\/22M1471304"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-024-02095-y"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1142\/S0218202518500276"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1111\/sapm.12470"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1051\/cocv\/2020046"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1142\/9789811266140_0004"},{"key":"ref12","first-page":"1","volume":"25","author":"Carrillo J. A.","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2970170"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.4208\/cicp.OA-2021-0144"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-014-9466-0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-025-02719-z"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/15M1026924"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1137\/21M1412323"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2008.2004422"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03311-7"},{"key":"ref21","unstructured":"F. Farnia and A. Ozdaglar, Do GANs always have Nash equilibria? Proc. Mach. Learn. Res. (PMLR), 119 (2020), pp. 3029\u20133039."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1142\/S0218202520500530"},{"key":"ref23","first-page":"1","volume":"22","author":"Fornasier M.","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/21M140941X"},{"key":"ref25","doi-asserted-by":"crossref","unstructured":"M. Fornasier, T. Klock, and K. Riedl, Convergence of anisotropic consensus-based optimization in mean-field law, in International Conference on the Applications of Evolutionary Computation, Springer, Cham, Switzerland, 2022, pp. 738\u2013754.","DOI":"10.1007\/978-3-031-02462-7_46"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/22M1527805"},{"key":"ref27","unstructured":"M. Fornasier and L. Sun, Regularity and Positivity of Solutions of the Consensus-Based Optimization Equation: Unconditional Global Convergence, preprint, arXiv:2502.01434, https:\/\/arxiv.org\/abs\/2502.01434, 2025."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1080\/03605302.2025.2459194"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-1665-5"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1051\/cocv\/2025060"},{"key":"ref31","unstructured":"G. Gidel, R. A. Hemmat, M. Pezeshki, R. L. Priol, G. Huang, S. Lacoste-Julien, and I. Mitliagkas, Negative momentum for improved game dynamics, Proc. Mach. Learn. Res. (PMLR), 89, (2019), pp. 1802\u20131811, https:\/\/proceedings.mlr.press\/v89\/gidel19a.html."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2009.2014275"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-022-01910-8"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s00211-021-01174-y"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1142\/S0218202522500130"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.1999.782545"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1142\/S021820252550037X"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1137\/S0036144500378302"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1090.001.0001"},{"key":"ref41","unstructured":"Y.P. Hsieh, P. Mertikopoulos, and V. Cevher, The limits of min-max optimization algorithms: Convergence to spurious non-critical sets, Proc. Mach. Learn. Res. (PMLR), 139 (2021), pp. 4337\u20134348, https:\/\/proceedings.mlr.press\/v139\/hsieh21a.html."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.aml.2024.109372"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1051\/cocv\/2025056"},{"key":"ref44","unstructured":"H. Huang, H. Kouhkouh, and L. Sun, Faithful Global Convergence for the Rescaled Consensus\u2013based Optimization, preprint, arXiv:2503.08578, 2025."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1002\/mma.8279"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s00245-023-09983-3"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1137\/22M1543367"},{"key":"ref48","author":"Huang H.","journal-title":"Commun. Pure Appl. Anal."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1137\/24M170644X"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2018.00057"},{"key":"ref51","volume-title":"Robust and Flexible Scheduling with Evolutionary Computation","author":"Jensen M. T.","year":"2001"},{"key":"ref52","unstructured":"C. Jin, P. Netrapalli, and M. Jordan, What is local optimality in nonconvex-nonconcave minimax optimization?  Proc. Mach. Learn. Res. (PMLR), 119, (2020), pp. 4880\u20134889, https:\/\/proceedings.mlr.press\/v119\/jin20e.html."},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1995.488968"},{"key":"ref54","first-page":"1576","author":"Laskari E.","year":"2002","journal-title":"Proceedings of the 2002 Congress on Evolutionary Computation. CEC\u201902, Vol. 2"},{"key":"ref55","unstructured":"A. Letcher, On the impossibility of global convergence in multi-loss optimization, in International Conference on Learning Representations, 2021, https:\/\/openreview.net\/forum?id=NQbnPjPYaG6."},{"key":"ref56","unstructured":"S. Liu, S. Lu, X. Chen, Y. Feng, K. Xu, A. Al-Dujaili, M. Hong, and U.M. O\u2019Reilly, Min-max optimization without gradients: Convergence and applications to black-box evasion and poisoning attacks, Proc. Mach. Learn. Res. (PMLR),119, (2020), pp. 6282\u20136293, https:\/\/proceedings.mlr.press\/v119\/liu20j.html."},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2245125"},{"key":"ref58","unstructured":"D. Madras, E. Creager, T. Pitassi, and R. Zemel, Learning adversarially fair and transferable representations, Proc. Mach. Learn. Res. (PMLR), 80, (2018), pp. 3384\u20133393."},{"key":"ref59","unstructured":"A. Madry, A. Makelov, L. Schmidt, D. Tsipras, and A. Vladu, Towards deep learning models resistant to adversarial attacks, in International Conference on Learning Representations, 2018, https:\/\/openreview.net\/forum?id=rJzIBfZAb."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-018-1326-9"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/075"},{"key":"ref62","volume-title":"Game Theory: Analysis of Conflict","author":"Myerson R. B.","year":"1997"},{"key":"ref63","doi-asserted-by":"crossref","unstructured":"J. F. Nash, Jr., Equilibrium points in n-person games, Proc. Natl. Acad. Sci. USA, 36 (1950), pp. 48\u201349.","DOI":"10.1073\/pnas.36.1.48"},{"key":"ref64","unstructured":"S. Omidshafiei, J. Pazis, C. Amato, J. P. How, and J. Vian, Deep decentralized multi-task multi-agent reinforcement learning under partial observability,  Proc. Mach. Learn. Res. (PMLR), 70 (2017), pp. 2681\u20132690."},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1142\/S0218202517400061"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3003851"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1017\/S0956792523000293"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.3934\/mbe.2020320"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-2025-2_2"},{"key":"ref70","volume-title":"Theory of Games and Economic Behavior","author":"Von Neumann J.","year":"2007"},{"key":"ref71","unstructured":"Y. Wang, G. Zhang, and J. Ba, On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach, preprint, arXiv:1910.07512, 2019."},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1137\/23M1568168"},{"key":"ref73","first-page":"1153","volume-title":"Advances in Neural Information Processing Systems, Vol. 33","author":"Yang J.","year":"2020"},{"key":"ref74","first-page":"1","volume":"23","author":"Zhang G.","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref75","first-page":"54075","volume-title":"Advances in Neural Information Processing Systems, Vol. 36","author":"Zheng T.","year":"2023"}],"container-title":["SIAM Journal on Control and Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/25M1766760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T13:23:14Z","timestamp":1787318594000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/25M1766760"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,27]]},"references-count":75,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1137\/25M1766760"],"URL":"https:\/\/doi.org\/10.1137\/25m1766760","relation":{},"ISSN":["0363-0129","1095-7138"],"issn-type":[{"value":"0363-0129","type":"print"},{"value":"1095-7138","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,27]]}}}