{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T16:53:28Z","timestamp":1771001608136,"version":"3.50.1"},"reference-count":42,"publisher":"Institute for Operations Research and the Management Sciences (INFORMS)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["INFORMS Journal on Computing"],"published-print":{"date-parts":[[2013,8]]},"abstract":"<jats:p>In the context of multistage stochastic optimization problems, we propose a hybrid strategy for generalizing to nonlinear decision rules, using machine learning, a finite data set of constrained vector-valued recourse decisions optimized using scenario-tree techniques from multistage stochastic programming. The decision rules are based on a statistical model inferred from a given scenario-tree solution and are selected by out-of-sample simulation given the true problem. Because the learned rules depend on the given scenario tree, we repeat the procedure for a large number of randomly generated scenario trees and then select the best solution (policy) found for the true problem. The scheme leads to an ex post selection of the scenario tree itself. Numerical tests evaluate the dependence of the approach on the machine learning aspects and show cases where one can obtain near-optimal solutions, starting with a \u201cweak\u201d scenario-tree generator that randomizes the branching structure of the trees.<\/jats:p>","DOI":"10.1287\/ijoc.1120.0516","type":"journal-article","created":{"date-parts":[[2012,8,15]],"date-time":"2012-08-15T04:57:36Z","timestamp":1345006656000},"page":"488-501","source":"Crossref","is-referenced-by-count":15,"title":["Scenario Trees and Policy Selection for Multistage Stochastic Programming Using Machine Learning"],"prefix":"10.1287","volume":"25","author":[{"given":"Boris","family":"Defourny","sequence":"first","affiliation":[{"name":"Department of Operations Research and Financial Engineering, Princeton University, Princeton, New Jersey 08544"}]},{"given":"Damien","family":"Ernst","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, University of Li\u00e8ge, 4000 Li\u00e8ge, Belgium"}]},{"given":"Louis","family":"Wehenkel","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, University of Li\u00e8ge, 4000 Li\u00e8ge, Belgium"}]}],"member":"109","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"B2","volume-title":"Dynamic Programming and Optimal Control","author":"Bertsekas DP","year":"2005","edition":"3"},{"key":"B3","volume-title":"Neuro-Dynamic Programming","author":"Berstsekas DP","year":"1996"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.9.2.111"},{"key":"B5","volume-title":"Introduction to Stochastic Programming","author":"Birge JR","year":"1997"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1201\/9781439821091"},{"key":"B7","unstructured":"Chiralaksanakul A. Monte Carlo methods for multi-stage stochastic programs. (2003) . Ph.D. thesis, University of Texas at Austin, Austin"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390175"},{"key":"B9","unstructured":"Defourny B. Machine learning solution methods for multistage stochastic programming. (2010) . Ph.D. thesis, University of Li\u00e8ge, Li\u00e8ge, Belgium"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04944-6_6"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-60960-165-2.ch006"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1201\/9781420081923"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1023\/A:1019206915174"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1007\/BF02592156"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84800-155-8_7"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-007-0197-2"},{"key":"B19","first-page":"139","volume-title":"Stochastic Programming\u2014The State of the Art, In Honor of George B. Dantzig","author":"Heitsch H","year":"2011"},{"issue":"2","key":"B20","first-page":"185","volume":"44","author":"Hilli P","year":"2008","journal-title":"Kybernetika"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.47.2.295.9834"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1080.0623"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88965-6"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(00)00261-7"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1080\/02331931003700756"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6377(98)00054-6"},{"key":"B27","first-page":"257","volume-title":"Stochastic Programming\u2014The State of the Art, In Honor of George B. Dantzig","author":"Mulvey JM","year":"2011"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.01.017"},{"issue":"1","key":"B29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1978.tb01643.x","volume":"40","author":"O'Hagan A","year":"1978","journal-title":"J. Roy. Statist. Soc."},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1515\/156939603322663321"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1040.0114"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-007-0113-9"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1002\/9781118029176"},{"key":"B35","volume-title":"Gaussian Processes for Machine Learning","author":"Rasmussen CE","year":"2006"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1287\/moor.16.1.119"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1007\/s001860300280"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718751"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390286"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01551-9"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.02.001"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718799"}],"container-title":["INFORMS Journal on Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubsonline.informs.org\/doi\/pdf\/10.1287\/ijoc.1120.0516","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,28]],"date-time":"2024-04-28T12:18:46Z","timestamp":1714306726000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubsonline.informs.org\/doi\/10.1287\/ijoc.1120.0516"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,8]]},"references-count":42,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2013,8]]}},"alternative-id":["10.1287\/ijoc.1120.0516"],"URL":"https:\/\/doi.org\/10.1287\/ijoc.1120.0516","relation":{},"ISSN":["1091-9856","1526-5528"],"issn-type":[{"value":"1091-9856","type":"print"},{"value":"1526-5528","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,8]]}}}