{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T19:35:28Z","timestamp":1787340928049,"version":"build-2736575974"},"reference-count":73,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"1","funder":[{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-19-1-0283"],"award-info":[{"award-number":["FA9550-19-1-0283"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-22-1-0244"],"award-info":[{"award-number":["FA9550-22-1-0244"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS2053489"],"award-info":[{"award-number":["DMS2053489"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Optim."],"published-print":{"date-parts":[[2024,3,31]]},"abstract":"<jats:p>Abstract.<\/jats:p>\n                  <jats:p>We consider stochastic optimization under distributional uncertainty, where the unknown distributional parameter is estimated from streaming data that arrive sequentially over time. Moreover, data may depend on the decision at the time when they are generated. For both decision-independent and decision-dependent uncertainties, we propose an approach to jointly estimate the distributional parameter via Bayesian posterior distribution and update the decision by applying stochastic gradient descent (SGD) on the Bayesian average of the objective function. Our approach converges asymptotically over time and achieves the convergence rates of classical SGD in the decision-independent case. We demonstrate the empirical performance of our approach on both synthetic test problems and a classical newsvendor problem.<\/jats:p>","DOI":"10.1137\/22m1478951","type":"journal-article","created":{"date-parts":[[2024,1,25]],"date-time":"2024-01-25T05:48:55Z","timestamp":1706161735000},"page":"389-418","source":"Crossref","is-referenced-by-count":17,"title":["Bayesian Stochastic Gradient Descent for Stochastic Optimization with Streaming Input Data"],"prefix":"10.1137","volume":"34","author":[{"given":"Tianyi","family":"Liu","sequence":"first","affiliation":[{"name":"H. Milton School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6967-8237","authenticated-orcid":true,"given":"Yifan","family":"Lin","sequence":"additional","affiliation":[{"name":"H. Milton School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5399-6508","authenticated-orcid":true,"given":"Enlu","family":"Zhou","sequence":"additional","affiliation":[{"name":"H. Milton School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2024,1,25]]},"reference":[{"key":"ref1","unstructured":"S. Agrawal  and \nN. Goyal  , Analysis of Thompson sampling for the multi-armed bandit problem, in Proceedings of the 25th Annual Conference on Learning Theory, Vol. 23, 2012, pp. 39.1\u201339.26."},{"key":"ref2","unstructured":"A. Ajalloeian  and \nS. U. Stich  , Analysis of SGD with Biased Gradient Estimators, in Workshop on \u201cBeyond First Order Methods in ML Systems\u201d at the 37th International Conference on Machine Learning, preprint, arXiv:2008.00051, 2020."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1040.0228"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1287\/educ.2015.0134"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1287\/moor.12.2.224"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1155\/S1048953301000284"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-017-1125-8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jspi.2014.07.009"},{"key":"ref9","volume-title":"Perturbation Analysis of Optimization Problems","author":"Bonnans J. F.","year":"2013"},{"key":"ref10","first-page":"9","volume":"17","author":"Bottou L.","year":"1998","journal-title":"Online Learning in Neural Networks"},{"key":"ref11","unstructured":"S. Bubeck , \nO. Dekel , \nT. Koren , and \nY. Peres  , Bandit convex optimization: \\(\\sqrt{T}\\) regret in one dimension, in Proceedings of the 28th Annual Conference on Learning Theory, Vol. 40, 2015, pp. 266\u2013278."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1051\/proc\/201551016"},{"key":"ref13","unstructured":"J. Cutler , \nM. D\u00edaz , and \nD. Drusvyatskiy  , Stochastic Approximation with Decision-Dependent Distributions: Asymptotic Normality and Optimality, preprint, arXiv:2207.04173, 2022."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1090.0741"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1287"},{"key":"ref16","first-page":"2121","volume":"12","author":"Duchi J.","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref17","unstructured":"J. Dupacov\u00e1  , Optimization under exogenous and endogenous uncertainty, in Proceedings of the 24th International conference on Mathematical Methods in Economics, 2006, pp. 131\u2013136."},{"key":"ref18","first-page":"2666","volume":"20","author":"Durmus A.","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3150\/18-BEJ1073"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1214\/16-AAP1257"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1017\/9781108591034"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/nav.21778"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9991(80)90084-4"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-017-1172-1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2018.3213"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/nav.20313"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.03.019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/120880811"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1214\/009053606000001172"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/0377-2217(95)00309-6"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-006-0715-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2013.1713"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2018.3140"},{"key":"ref34","volume-title":"Advances in Neural Information Processing Systems","volume":"20","author":"Hazan E.","year":"2007"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10287-018-0330-0"},{"key":"ref36","unstructured":"Z. Izzo , \nL. Ying , and \nJ. Zou  , How to learn when data reacts to your model: Performative gradient descent, in Proceedings of the 38th International Conference on Machine Learning,  \nM. Meila  and \nT. Zhang  , eds. Curran Associates, Red Hook, NY, 2021, pp. 4641\u20134650."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0929-7"},{"key":"ref38","unstructured":"P. Juan , \nZ. Tijana , \nM.D. Celestine , and \nH. Moritz  , Performative prediction, in Proceedings of the 37th International Conference on Machine Learning,  \nH. D. III  and \nA. Singh  , eds. IEEE, Piscataway, NJ, 2020, pp. 7599\u20137609."},{"key":"ref39","volume-title":"Stochastic Approximation and Recursive Algorithms and Applications","author":"Kushner H.","year":"2003"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2018.01.006"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s00186-012-0396-3"},{"key":"ref42","volume-title":"Theory of Point Estimation","author":"Lehmann E. L.","year":"1998"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2021.3085852"},{"key":"ref44","doi-asserted-by":"crossref","unstructured":"T. Liu , \nY. Lin , and \nE. Zhou  , A Bayesian approach to online simulation optimization with streaming input data, in Proceedings of the 2021 Winter Simulation Conference,  \nS. Kim , \nB. Feng , \nK. S. S. Masoud , \nZ. Zheng , \nC. Szabo , and \nM. Loper  , eds. IEEE, Piscataway, NJ, 2021.","DOI":"10.1109\/WSC52266.2021.9715392"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11590-020-01574-3"},{"key":"ref46","first-page":"4929","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Mendler-D\u00fcnner C.","year":"2020"},{"key":"ref47","unstructured":"J. P. Miller , \nJ. C. Perdomo , and \nT. Zrnic  , Outside the echo chamber: Optimizing the performative risk, in Proceedings of the 38th International Conference on Machine Learning, Vol. 139,  \nM. Meila  and \nT. Zhang  , eds. Curran Associates, Red Hook, NY, 2021, pp. 7710\u20137720."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1137\/17M1110560"},{"key":"ref49","author":"Noyan N.","year":"2018","journal-title":"Optimization Online"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1007-8"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.792.304"},{"key":"ref52","first-page":"1674","volume":"65","author":"Raginsky M.","year":"2017","journal-title":"Proc. Mach. Learn. Res. (PMLR)"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1561\/2200000018"},{"key":"ref54","unstructured":"O. Shamir  and \nT. Zhang  , Stochastic gradient descent for non-smooth optimization: Convergence results and optimal averaging schemes, in Proceedings of the 30th International Conference on Machine Learning, Vol. 28,  \nS. Dasgupta  and \nD. McAllester  , eds. Curran Associates, Red Hook, NY, 2013, pp. 71\u201379."},{"key":"ref55","doi-asserted-by":"crossref","unstructured":"A. Shapiro , \nD. Dentcheva , and \nA. Ruszczynski  , Lectures on Stochastic Programming: Modeling and Theory, 3rd ed. SIAM, Philadelphia, 2021.","DOI":"10.1137\/1.9781611976595"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1137\/21M1465548"},{"key":"ref57","doi-asserted-by":"crossref","unstructured":"E. Song  and \nU. V. Shanbhag  , Stochastic approximation for simulation optimization under input uncertainty with streaming data, in Proceedings of the 2019 Winter Simulation Conference,  \nN. Mustafee , \nK.H. Bae , \nS. Lazarova-Molnar , \nM. Rabe , \nC. Szabo , \nP. Haas , and \nY.J. Son  , eds. IEEE, Piscataway, NJ, 2019, pp. 3597\u20133608.","DOI":"10.1109\/WSC40007.2019.9004677"},{"key":"ref58","first-page":"430","volume":"61","author":"Van Parys B. P.","year":"2015","journal-title":"IEEE Trans. Automat. Control"},{"key":"ref59","unstructured":"H. Wang , \nX. Zhang , and \nS. H. Ng  , A Nonparametric Bayesian Approach for Simulation Optimization with Input Uncertainty, preprint, arXiv:2008.02154, 2020."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s10287-012-0147-1"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2014.1314"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1023\/A:1019296422231"},{"key":"ref63","doi-asserted-by":"crossref","unstructured":"D. Wu  and \nE. Zhou  , Ranking and selection under input uncertainty: A budget allocation formulation, in Proceedings of the 2017 Winter Simulation Conference,  \nW. K. V. Chan , \nA. D\u2019Ambrogio , \nG. Zacharewicz , \nN. Mustafee , \nG. Wainer , and \nE. Page  , eds. IEEE, Piscataway, NJ, 2017, pp. 2245\u20132256.","DOI":"10.1109\/WSC.2017.8247956"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1137\/16M1101933"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1080\/24725854.2019.1659524"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2791425"},{"key":"ref67","first-page":"2505","volume-title":"Advances in Neural Information Processing Systems","author":"Xu H.","year":"2010"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2017.2711553"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3030884"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-020-01580-4"},{"key":"ref71","doi-asserted-by":"crossref","unstructured":"E. Zhou  and \nT. Liu  , Online quantification of input uncertainty for parametric models, in Proceedings of the 2018 Winter Simulation Conference,  \nM. Rabe , \nA. A. Juan , \nN. Mustafee , \nA. Skoogh , \nS. Jain , and \nB. Johansson  , eds. IEEE, Piscataway, NJ, 2018, pp. 1587\u20131598.","DOI":"10.1109\/WSC.2018.8632447"},{"key":"ref72","doi-asserted-by":"crossref","unstructured":"E. Zhou  and \nW. Xie  , Simulation optimization when facing input uncertainty, in Proceedings of the 2015 Winter Simulation Conference,  \nL. Yilmaz , \nW. K. V. Chan , \nI. Moon , \nT. M. K. Roeder , \nC. Macal , and \nM. D. Rossetti  , eds. IEEE, Piscataway, NJ, 2015, pp. 3714\u20133724.","DOI":"10.1109\/WSC.2015.7408529"},{"key":"ref73","unstructured":"M. Zinkevich  , Online convex programming and generalized infinitesimal gradient ascent, in Proceedings of the 20th International Conference on Machine Learning, AAAI Press, Menlo Park, CA, 2003, pp. 928\u2013936."}],"container-title":["SIAM Journal on Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/22M1478951","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T18:56:31Z","timestamp":1787338591000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/22M1478951"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,25]]},"references-count":73,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,3,31]]}},"alternative-id":["10.1137\/22M1478951"],"URL":"https:\/\/doi.org\/10.1137\/22m1478951","relation":{},"ISSN":["1052-6234","1095-7189"],"issn-type":[{"value":"1052-6234","type":"print"},{"value":"1095-7189","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,25]]}}}