{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T03:30:45Z","timestamp":1780543845854,"version":"3.54.1"},"reference-count":46,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T00:00:00Z","timestamp":1756339200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>This paper introduces a novel framework for Distributionally Robust Bayesian Optimization (DRBO) with continuous context that integrates optimal transport theory and entropic regularization. We propose the sampling from the Wasserstein Barycenter Bayesian Optimization (SWBBO) method to deal with uncertainty about the context; that is, the unknown stochastic component affecting the observations of the black-box objective function. This approach captures the geometric structure of the underlying distributional uncertainty and enables robust acquisition strategies without incurring excessive computational costs. The method incorporates adaptive robustness scheduling, Lipschitz regularization, and efficient barycenter construction to balance exploration and exploitation. Theoretical analysis establishes convergence guarantees for the robust Bayesian Optimization acquisition function. Empirical evaluations on standard global optimization problems and real-life inspired benchmarks demonstrate that SWBBO consistently achieves faster convergence, good final regret, and greater stability than other recently proposed methods for DRBO with continuous context. Indeed, SWBBO outperforms all of them in terms of both optimization performance and robustness under repeated evaluations.<\/jats:p>","DOI":"10.3390\/make7030090","type":"journal-article","created":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T09:08:52Z","timestamp":1756458532000},"page":"90","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Distributionally Robust Bayesian Optimization via Sinkhorn-Based Wasserstein Barycenter"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1875-7565","authenticated-orcid":false,"given":"Iman","family":"Seyedi","sequence":"first","affiliation":[{"name":"Department of Computer Science Systems and Communication, University of Milano-Bicocca, 20126 Milan, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1431-576X","authenticated-orcid":false,"given":"Antonio","family":"Candelieri","sequence":"additional","affiliation":[{"name":"Department of Economics Management and Statistics, University of Milano-Bicocca, 20126 Milan, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco","family":"Archetti","sequence":"additional","affiliation":[{"name":"Department of Computer Science Systems and Communication, University of Milano-Bicocca, 20126 Milan, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Garnett, R. (2023). Bayesian Optimization, Cambridge University Press.","DOI":"10.1017\/9781108348973"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Frazier, P.I. (2018). Bayesian Optimization. Recent Advances in Optimization and Modeling of Contemporary Problems, Proceedings of the INFORMS Annual Meeting, Phoenix, AZ, USA, 4\u20137 November 2018, INFORMS.","DOI":"10.1287\/educ.2018.0188"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Archetti, F., and Candelieri, A. (2019). Bayesian Optimization and Data Science, Springer International Publishing.","DOI":"10.1007\/978-3-030-24494-1"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Seyedi, I., Candelieri, A., Messina, E., and Archetti, F. (2025). Wasserstein Distributionally Robust Optimization for Chance-Constrained Facility Location Under Uncertain Demand. Mathematics, 13.","DOI":"10.3390\/math13132144"},{"key":"ref_5","unstructured":"Blanchet, J., Li, J., Lin, S., and Zhang, X. (2024). Distributionally Robust Optimization and Robust Statistics. arXiv."},{"key":"ref_6","first-page":"33689","article-title":"Distributionally robust optimization with data geometry","volume":"35","author":"Liu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_7","unstructured":"Kirschner, J., Bogunovic, I., Jegelka, S., and Krause, A. (2020, January 26\u201328). Distributionally robust Bayesian optimization. Proceedings of the International Conference on Artificial Intelligence and Statistics, PMLR, Valencia, Spain. Available online: http:\/\/proceedings.mlr.press\/v108\/kirschner20a.html."},{"key":"ref_8","unstructured":"Husain, H., Nguyen, V., and van den Hengel, A. (2025, July 17). Distributionally Robust Bayesian Optimization with \u03d5-Divergences. Available online: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/3feb8ed3c33c3310b45f80be7dfef707-Supplemental-Conference.pdf."},{"key":"ref_9","unstructured":"Micheli, F., Balta, E.C., Tsiamis, A., and Lygeros, J. (2025). Wasserstein Distributionally Robust Bayesian Optimization with Continuous Context. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1561\/2200000073","article-title":"Computational optimal transport: With applications to data science","volume":"11","author":"Cuturi","year":"2019","journal-title":"Found. Trends Mach. Learn."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5802\/ojmo.15","article-title":"Frameworks and Results in Distributionally Robust Optimization","volume":"3","author":"Rahimian","year":"2022","journal-title":"Open J. Math. Optim."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"604","DOI":"10.1287\/mnsc.2017.2952","article-title":"Adaptive Distributionally Robust Optimization","volume":"65","author":"Bertsimas","year":"2019","journal-title":"Manag. Sci."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"11263","DOI":"10.1007\/s12652-023-04640-7","article-title":"Wasserstein enabled Bayesian optimization of composite functions","volume":"14","author":"Candelieri","year":"2023","journal-title":"J. Ambient Intell. Humaniz. Comput."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2232","DOI":"10.3390\/make6040110","article-title":"Bayesian Optimization Using Simulation-Based Multiple Information Sources over Combinatorial Structures","volume":"6","author":"Sabbatella","year":"2024","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"ref_15","unstructured":"Cuturi, M., and Doucet, A. (2014, January 22\u201324). Fast computation of Wasserstein Barycenters. Proceedings of the International Conference on Machine Learning, PMLR, Beijing, China."},{"key":"ref_16","unstructured":"Mallasto, A., and Feragen, A. (2017, January 4\u20139). Learning from uncertain curves: The 2-Wasserstein metric for Gaussian processes. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Lovric, M. (2011). Kullback-Leibler Divergence. International Encyclopedia of Statistical Science, Springer.","DOI":"10.1007\/978-3-642-04898-2"},{"key":"ref_18","unstructured":"Cuturi, M. (2013, January 5\u20138). Sinkhorn distances: Lightspeed computation of optimal transport. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1007\/978-3-030-49988-4_28","article-title":"A Stable Alternative to Sinkhorn\u2019s Algorithm for Regularized Optimal Transport","volume":"Volume 12095","author":"Kononov","year":"2020","journal-title":"Mathematical Optimization Theory and Operations Research, Lecture Notes in Computer Science"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"904","DOI":"10.1137\/100805741","article-title":"Barycenters in the Wasserstein Space","volume":"43","author":"Agueh","year":"2011","journal-title":"SIAM J. Math. Anal."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1007\/s00245-022-09911-x","article-title":"Kantorovich\u2013Rubinstein Distance and Barycenter for Finitely Supported Measures: Foundations and Algorithms","volume":"87","author":"Heinemann","year":"2023","journal-title":"Appl. Math. Optim."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1007\/s10107-017-1125-8","article-title":"Data-driven robust optimization","volume":"167","author":"Bertsimas","year":"2018","journal-title":"Math. Program."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/s10107-017-1172-1","article-title":"Data-driven distributionally robust optimization using the Wasserstein metric: Performance guarantees and tractable reformulations","volume":"171","author":"Kuhn","year":"2018","journal-title":"Math. Program."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1500","DOI":"10.1287\/moor.2021.1178","article-title":"Optimal Transport-Based Distributionally Robust Optimization: Structural Properties and Iterative Schemes","volume":"47","author":"Blanchet","year":"2022","journal-title":"Math. Oper. Res."},{"key":"ref_25","unstructured":"Netessine, S., Shier, D., and Greenberg, H.J. (2019). Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning. Operations Research & Management Science in the Age of Analytics, Proceedings of INFORMS Annual Meeting, Washington, DC, USA, 20\u201323 October 2019, Informs."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1177","DOI":"10.1287\/opre.2022.2383","article-title":"Wasserstein Distributionally Robust Optimization and Variation Regularization","volume":"72","author":"Gao","year":"2024","journal-title":"Oper. Res."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1279","DOI":"10.1137\/21M1465548","article-title":"Bayesian Distributionally Robust Optimization","volume":"33","author":"Shapiro","year":"2023","journal-title":"SIAM J. Optim."},{"key":"ref_28","unstructured":"Kirschner, J., Mutny, M., Hiller, N., Ischebeck, R., and Krause, A. (2019, January 9\u201315). Adaptive and safe Bayesian optimization in high dimensions via one-dimensional subspaces. Proceedings of the International Conference on Machine Learning, PMLR, Long Beach, CA, USA."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"20345","DOI":"10.1007\/s10668-024-04767-3","article-title":"Circular closed-loop supply chain network design considering 3D printing and PET bottle waste","volume":"27","author":"Seyedi","year":"2024","journal-title":"Environ. Dev. Sustain."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"410","DOI":"10.1287\/opre.2022.2330","article-title":"Technical Note\u2014Data-Driven Chance Constrained Programs over Wasserstein Balls","volume":"72","author":"Chen","year":"2024","journal-title":"Oper. Res."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1007\/s40430-023-04106-z","article-title":"Numerical modeling and optimization of pressure drop and heat transfer rate in a polymer fuel cell parallel cooling channel","volume":"45","author":"Arabkoohsar","year":"2023","journal-title":"J. Braz. Soc. Mech. Sci. Eng."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1248","DOI":"10.1287\/moor.2015.0776","article-title":"Robust Sensitivity Analysis for Stochastic Systems","volume":"41","author":"Lam","year":"2016","journal-title":"Math. Oper. Res."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Aleman, D., Thiele, A., Smith, J.C., and Greenberg, H.J. (2015). Data-Driven Stochastic Programming Using Phi-Divergences. The Operations Research Revolution, Informs.","DOI":"10.1287\/educ.2015"},{"key":"ref_34","unstructured":"Zhou, Z., Mertikopoulos, P., Bambos, N., Glynn, P., Ye, Y., Li, L.J., and Fei-Fei, L. (2018, January 10\u201315). Distributed asynchronous optimization with unbounded delays: How slow can you go?. Proceedings of the International Conference on Machine Learning, PMLR, Stockholm, Sweden."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2291","DOI":"10.1287\/opre.2022.2326","article-title":"Finite-sample guarantees for Wasserstein distributionally robust optimization: Breaking the curse of dimensionality","volume":"71","author":"Gao","year":"2023","journal-title":"Oper. Res."},{"key":"ref_36","unstructured":"Altschuler, J., Niles-Weed, J., and Rigollet, P. (2017, January 4\u20139). Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_37","unstructured":"Snoek, J., Larochelle, H., and Adams, R.P. (2012, January 3\u20136). Practical bayesian optimization of machine learning algorithms. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"3713","DOI":"10.1007\/s10994-021-06019-1","article-title":"Bayesian optimization with safety constraints: Safe and automatic parameter tuning in robotics","volume":"112","author":"Berkenkamp","year":"2023","journal-title":"Mach. Learn."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Williams, C.K., and Rasmussen, C.E. (2006). Gaussian Processes for Machine Learning, MIT Press. [2nd ed.].","DOI":"10.7551\/mitpress\/3206.001.0001"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Santambrogio, F. (2015). Optimal Transport for Applied Mathematicians: Calculus of Variations, PDEs, and Modeling, Progress in Nonlinear Differential Equations and Their Applications; Springer International Publishing.","DOI":"10.1007\/978-3-319-20828-2"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"A1111","DOI":"10.1137\/141000439","article-title":"Iterative Bregman Projections for Regularized Transportation Problems","volume":"37","author":"Benamou","year":"2015","journal-title":"SIAM J. Sci. Comput."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Pham, T., Dal Poz Kou\u0159imsk\u00e1, H., and Wagner, H. (2025). Bregman\u2013Hausdorff Divergence: Strengthening the Connections Between Computational Geometry and Machine Learning. Mach. Learn. Knowl. Extr., 7.","DOI":"10.3390\/make7020048"},{"key":"ref_43","unstructured":"(2025, July 17). POT: Python Optimal Transport\u2014POT Python Optimal Transport 0.9.5 Documentation. Available online: https:\/\/pythonot.github.io\/releases.html."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1007\/s10589-023-00458-3","article-title":"Simple approximative algorithms for free-support Wasserstein barycenters","volume":"85","author":"Lindheim","year":"2023","journal-title":"Comput. Optim. Appl."},{"key":"ref_45","unstructured":"Srinivas, N., Krause, A., Kakade, S.M., and Seeger, M. (2009). Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design. arXiv."},{"key":"ref_46","unstructured":"Howard, S., Potaptchik, P., and Deligiannidis, G. (2025). Schr\u00f6dinger Bridge Matching for Tree-Structured Costs and Entropic Wasserstein Barycentres. arXiv."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/3\/90\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:34:49Z","timestamp":1760034889000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/3\/90"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,28]]},"references-count":46,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["make7030090"],"URL":"https:\/\/doi.org\/10.3390\/make7030090","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,28]]}}}