{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:46:18Z","timestamp":1781279178208,"version":"3.54.1"},"reference-count":92,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T00:00:00Z","timestamp":1712707200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation","award":["CCF-1422910, CCF-1535967, CCF-1733556, CCF-1910321, IIS-1617590, IIS-1618714, IIS-1718457, SES-1919453, RI-2312342, and RI-1901403"],"award-info":[{"award-number":["CCF-1422910, CCF-1535967, CCF-1733556, CCF-1910321, IIS-1617590, IIS-1618714, IIS-1718457, SES-1919453, RI-2312342, and RI-1901403"]}]},{"name":"Microsoft Research Faculty Fellowship"},{"name":"Amazon Research Award"},{"name":"AWS Machine Learning Research Award"},{"name":"Bloomberg Research Grant"},{"name":"NSF Graduate Research Fellowship"},{"name":"Carnegie Mellon University\u2019s Center for Machine Learning and Health"},{"name":"ARO","award":["W911NF2210266, W911NF-17-1-0082, and W911NF2010081"],"award-info":[{"award-number":["W911NF2210266, W911NF-17-1-0082, and W911NF2010081"]}]},{"name":"ONR","award":["N00014-23-1-2876"],"award-info":[{"award-number":["N00014-23-1-2876"]}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"crossref","award":["HR0011202000"],"award-info":[{"award-number":["HR0011202000"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Vannevar Bush Faculty Fellowship"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["J. ACM"],"published-print":{"date-parts":[[2024,4,30]]},"abstract":"<jats:p>\n            Tree search algorithms, such as branch-and-bound, are the most widely used tools for solving combinatorial and non-convex problems. For example, they are the foremost method for solving (mixed) integer programs and constraint satisfaction problems. Tree search algorithms come with a variety of tunable parameters that are notoriously challenging to tune by hand. A growing body of research has demonstrated the power of using a data-driven approach to automatically optimize the parameters of tree search algorithms. These techniques use a\n            <jats:italic>training set<\/jats:italic>\n            of integer programs sampled from an application-specific instance distribution to find a parameter setting that has strong average performance over the training set. However, with too few samples, a parameter setting may have strong average performance on the training set but poor expected performance on future integer programs from the same application. Our main contribution is to provide the first\n            <jats:italic>sample complexity guarantees<\/jats:italic>\n            for tree search parameter tuning. These guarantees bound the number of samples sufficient to ensure that the average performance of tree search over the samples nearly matches its future expected performance on the unknown instance distribution. In particular, the parameters we analyze weight\n            <jats:italic>scoring rules<\/jats:italic>\n            used for variable selection. Proving these guarantees is challenging because tree size is a volatile function of these parameters: we prove that, for any discretization (uniform or not) of the parameter space, there exists a distribution over integer programs such that every parameter setting in the discretization results in a tree with exponential expected size, yet there exist parameter settings between the discretized points that result in trees of constant size. In addition, we provide data-dependent guarantees that depend on the volatility of these tree-size functions: our guarantees improve if the tree-size functions can be well approximated by simpler functions. Finally, via experiments, we illustrate that learning an optimal weighting of scoring rules reduces tree size.\n          <\/jats:p>","DOI":"10.1145\/3637840","type":"journal-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T11:39:28Z","timestamp":1703504368000},"page":"1-73","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Learning to Branch: Generalization Guarantees and Limits of Data-Independent Discretization"],"prefix":"10.1145","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9525-0103","authenticated-orcid":false,"given":"Maria-Florina","family":"Balcan","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1271-307X","authenticated-orcid":false,"given":"Travis","family":"Dick","sequence":"additional","affiliation":[{"name":"Google, New York, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8861-9366","authenticated-orcid":false,"given":"Tuomas","family":"Sandholm","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, United States, Strategic Machine, Inc., Pittsburgh, United States, Strategy Robot, Inc., Pittsburgh, United States, and Optimized Markets, Inc., Pittsburgh, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4891-1367","authenticated-orcid":false,"given":"Ellen","family":"Vitercik","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,10]]},"reference":[{"key":"e_1_3_4_2_1","volume-title":"Constraint Integer Programming","author":"Achterberg Tobias","year":"2007","unstructured":"Tobias Achterberg. 2007. Constraint Integer Programming. Ph.D. Dissertation. Technische Universit\u00e4t Berlin."},{"key":"e_1_3_4_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-008-0001-1"},{"key":"e_1_3_4_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.orl.2004.04.002"},{"key":"e_1_3_4_5_1","article-title":"Setting fair incentives to maximize improvement","author":"Ahmadi Saba","year":"2022","unstructured":"Saba Ahmadi, Hedyeh Beyhaghi, Avrim Blum, and Keziah Naggita. 2022. Setting fair incentives to maximize improvement. arXiv preprint arXiv:2203.00134 (2022).","journal-title":"arXiv preprint arXiv:2203.00134"},{"key":"e_1_3_4_6_1","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2016.0723"},{"key":"e_1_3_4_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04244-7_14"},{"key":"e_1_3_4_8_1","volume-title":"Neural Network Learning: Theoretical Foundations","author":"Anthony Martin","year":"2009","unstructured":"Martin Anthony and Peter Bartlett. 2009. Neural Network Learning: Theoretical Foundations. Cambridge University Press."},{"key":"e_1_3_4_9_1","volume-title":"Beyond Worst Case Analysis of Algorithms","author":"Balcan Maria-Florina","year":"2020","unstructured":"Maria-Florina Balcan. 2020. Data-driven algorithm design. In Beyond Worst Case Analysis of Algorithms, Tim Roughgarden (Ed.). Cambridge University Press. (Forthcoming)."},{"key":"e_1_3_4_10_1","article-title":"Learning to branch","author":"Balcan Maria-Florina","year":"2018","unstructured":"Maria-Florina Balcan, Travis Dick, Tuomas Sandholm, and Ellen Vitercik. 2018a. Learning to branch. In Proceedings of theInternational Conference on Machine Learning (ICML) (2018).","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"e_1_3_4_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2018.00064"},{"key":"e_1_3_4_12_1","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201922)","author":"Balcan Maria-Florina","year":"2022","unstructured":"Maria-Florina Balcan, Mikhail Khodak, Dravyansh Sharma, and Ameet Talwalkar. 2022. Provably tuning the ElasticNet across instances. In Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201922)."},{"key":"e_1_3_4_13_1","volume-title":"Proceedings of the Conference on Learning Theory (COLT\u201917)","author":"Balcan Maria-Florina","year":"2017","unstructured":"Maria-Florina Balcan, Vaishnavh Nagarajan, Ellen Vitercik, and Colin White. 2017. Learning-theoretic foundations of algorithm configuration for combinatorial partitioning problems. In Proceedings of the Conference on Learning Theory (COLT\u201917)."},{"key":"e_1_3_4_14_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201920)","author":"Balcan Maria-Florina","year":"2020","unstructured":"Maria-Florina Balcan, Travis Dick, and Manuel Lang. 2020a. Learning to link. In Proceedings of the International Conference on Learning Representations (ICLR\u201920)."},{"key":"e_1_3_4_15_1","volume-title":"Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI\u201920)","author":"Balcan Maria-Florina","year":"2020","unstructured":"Maria-Florina Balcan, Travis Dick, and Wesley Pegden. 2020b. Semi-bandit optimization in the dispersed setting. In Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI\u201920)."},{"key":"e_1_3_4_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5721"},{"key":"e_1_3_4_17_1","volume-title":"International Conference on Machine Learning (ICML\u201920)","author":"Balcan Maria-Florina","year":"2020","unstructured":"Maria-Florina Balcan, Tuomas Sandholm, and Ellen Vitercik. 2020d. Refined bounds for algorithm configuration: The knife-edge of dual class approximability. In International Conference on Machine Learning (ICML\u201920)."},{"key":"e_1_3_4_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17451"},{"key":"e_1_3_4_19_1","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201921)","author":"Balcan Maria-Florina F.","year":"2021","unstructured":"Maria-Florina F. Balcan, Mikhail Khodak, Dravyansh Sharma, and Ameet Talwalkar. 2021b. Learning-to-learn non-convex piecewise-Lipschitz functions. In Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201921)."},{"key":"e_1_3_4_20_1","article-title":"Data driven semi-supervised learning","author":"Balcan Maria-Florina F.","year":"2021","unstructured":"Maria-Florina F. Balcan and Dravyansh Sharma. 2021. Data driven semi-supervised learning. In Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS) (2021).","journal-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS)"},{"key":"e_1_3_4_21_1","volume-title":"Proceedings of the Conference on Learning Theory (COLT\u201922)","author":"Bartlett Peter","year":"2022","unstructured":"Peter Bartlett, Piotr Indyk, and Tal Wagner. 2022. Generalization bounds for data-driven numerical linear algebra. In Proceedings of the Conference on Learning Theory (COLT\u201922)."},{"key":"e_1_3_4_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-5060(08)70351-0"},{"key":"e_1_3_4_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58942-4_7"},{"key":"e_1_3_4_24_1","article-title":"Machine learning for combinatorial optimization: A methodological tour d\u2019horizon","author":"Bengio Yoshua","year":"2020","unstructured":"Yoshua Bengio, Andrea Lodi, and Antoine Prouvost. 2020b. Machine learning for combinatorial optimization: A methodological tour d\u2019horizon. European Journal of Operational Research (2020).","journal-title":"European Journal of Operational Research"},{"key":"e_1_3_4_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01584074"},{"key":"e_1_3_4_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-61551-2_66"},{"key":"e_1_3_4_27_1","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS\u201921)","author":"Blum Avrim","year":"2021","unstructured":"Avrim Blum, Chen Dan, and Saeed Seddighin. 2021. Learning complexity of simulated annealing. In Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS\u201921)."},{"key":"e_1_3_4_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93031-2_43"},{"key":"e_1_3_4_29_1","volume-title":"International Conference on Artificial Intelligence and Statistics (AISTATS\u201917)","author":"Cohen-Addad Vincent","year":"2017","unstructured":"Vincent Cohen-Addad and Varun Kanade. 2017. Online optimization of smoothed piecewise constant functions. In Proceedings of theInternational Conference on Artificial Intelligence and Statistics (AISTATS\u201917)."},{"key":"e_1_3_4_30_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611976465.35"},{"key":"e_1_3_4_31_1","article-title":"Lower bounds on the size of general branch-and-bound trees","author":"Dey Santanu S.","year":"2021","unstructured":"Santanu S. Dey, Yatharth Dubey, and Marco Molinaro. 2021b. Lower bounds on the size of general branch-and-bound trees. arXiv preprint arXiv:2103.09807 (2021).","journal-title":"arXiv preprint arXiv:2103.09807"},{"key":"e_1_3_4_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2015.08.018"},{"key":"e_1_3_4_33_1","first-page":"15554","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201919)","author":"Gasse Maxime","year":"2019","unstructured":"Maxime Gasse, Didier Ch\u00e9telat, Nicola Ferroni, Laurent Charlin, and Andrea Lodi. 2019. Exact combinatorial optimization with graph convolutional neural networks. In Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201919). 15554\u201315566."},{"key":"e_1_3_4_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01593767"},{"key":"e_1_3_4_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.disopt.2010.07.001"},{"key":"e_1_3_4_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(00)00081-3"},{"key":"e_1_3_4_37_1","doi-asserted-by":"publisher","DOI":"10.1137\/15M1050276"},{"key":"e_1_3_4_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(80)90051-X"},{"key":"e_1_3_4_39_1","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201914)","author":"He He","year":"2014","unstructured":"He He, Hal Daume III, and Jason M. Eisner. 2014. Learning to search in branch and bound algorithms. In Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201914)."},{"key":"e_1_3_4_40_1","volume-title":"Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI\u201901)","author":"Horvitz Eric","year":"2001","unstructured":"Eric Horvitz, Yongshao Ruan, Carla Gomez, Henry Kautz, Bart Selman, and Max Chickering. 2001. A Bayesian approach to tackling hard computational problems. In Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI\u201901)."},{"key":"e_1_3_4_41_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201919)","author":"Hsu Chen-Yu","year":"2019","unstructured":"Chen-Yu Hsu, Piotr Indyk, Dina Katabi, and Ali Vakilian. 2019. Learning-based frequency estimation algorithms. In Proceedings of the International Conference on Learning Representations (ICLR\u201919)."},{"key":"e_1_3_4_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-13520-0_23"},{"key":"e_1_3_4_43_1","first-page":"507","volume-title":"Proc. of LION-5","author":"Hutter Frank","year":"2011","unstructured":"Frank Hutter, Holger H. Hoos, and Kevin Leyton-Brown. 2011. Sequential model-based optimization for general algorithm configuration. In Proc. of LION-5. 507\u2013523."},{"key":"e_1_3_4_44_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2861"},{"key":"e_1_3_4_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2013.10.003"},{"key":"e_1_3_4_46_1","unstructured":"IBM ILOG Inc. 2007. CPLEX 11.0 Release Notes."},{"key":"e_1_3_4_47_1","unstructured":"IBM ILOG Inc. 2017. CPLEX 12.8 Parameters Reference."},{"key":"e_1_3_4_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01580225"},{"key":"e_1_3_4_49_1","volume-title":"Proceedings of the European Conference on Artificial Intelligence (ECAI\u201910)","author":"Kadioglu Serdar","year":"2010","unstructured":"Serdar Kadioglu, Yuri Malitsky, Meinolf Sellmann, and Kevin Tierney. 2010. ISAC-instance-specific algorithm configuration. In Proceedings of the European Conference on Artificial Intelligence (ECAI\u201910)."},{"key":"e_1_3_4_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10080"},{"key":"e_1_3_4_51_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/92"},{"key":"e_1_3_4_52_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/281"},{"key":"e_1_3_4_53_1","article-title":"Procrastinating with confidence: Near-optimal, anytime, adaptive algorithm configuration","author":"Kleinberg Robert","year":"2019","unstructured":"Robert Kleinberg, Kevin Leyton-Brown, Brendan Lucier, and Devon Graham. 2019. Procrastinating with confidence: Near-optimal, anytime, adaptive algorithm configuration. In Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS) (2019).","journal-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS)"},{"key":"e_1_3_4_54_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.13.9.723"},{"key":"e_1_3_4_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/18.930926"},{"key":"e_1_3_4_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59776-8_16"},{"key":"e_1_3_4_57_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1571-0653(04)00332-4"},{"key":"e_1_3_4_58_1","doi-asserted-by":"publisher","DOI":"10.2307\/1910129"},{"key":"e_1_3_4_59_1","first-page":"1","article-title":"An abstract model for branching and its application to mixed integer programming","author":"Bodic Pierre Le","year":"2017","unstructured":"Pierre Le Bodic and George Nemhauser. 2017. An abstract model for branching and its application to mixed integer programming. Mathematical Programming (2017), 1\u201337.","journal-title":"Mathematical Programming"},{"key":"e_1_3_4_60_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1701997114"},{"key":"e_1_3_4_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/1538902.1538906"},{"key":"e_1_3_4_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/352871.352879"},{"key":"e_1_3_4_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-40970-2_9"},{"key":"e_1_3_4_64_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00097-1"},{"key":"e_1_3_4_65_1","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.11.2.173"},{"key":"e_1_3_4_66_1","first-page":"353","volume-title":"Proceedings of the National Conference on Artificial Intelligence (AAAI\u201998)","author":"Lobjois L.","year":"1998","unstructured":"L. Lobjois and M. Lema\u00eetre. 1998. Branch and bound algorithm selection by performance prediction. In Proceedings of the National Conference on Artificial Intelligence (AAAI\u201998). San Jose, CA, 353\u2013358."},{"key":"e_1_3_4_67_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML\u201918)","author":"Lykouris Thodoris","year":"2018","unstructured":"Thodoris Lykouris and Sergei Vassilvitskii. 2018. Competitive caching with machine learned advice. In Proceedings of the International Conference on Machine Learning (ICML\u201918)."},{"key":"e_1_3_4_68_1","doi-asserted-by":"publisher","DOI":"10.5802\/afst.961"},{"key":"e_1_3_4_69_1","first-page":"464","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201918)","author":"Mitzenmacher Michael","year":"2018","unstructured":"Michael Mitzenmacher. 2018. A model for learned bloom filters and optimizing by sandwiching. In Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201918). 464\u2013473."},{"key":"e_1_3_4_70_1","doi-asserted-by":"publisher","DOI":"10.5555\/2371238"},{"key":"e_1_3_4_71_1","first-page":"9661","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201918)","author":"Purohit Manish","year":"2018","unstructured":"Manish Purohit, Zoya Svitkina, and Ravi Kumar. 2018. Improving online algorithms via ML predictions. In Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201918). 9661\u20139670."},{"key":"e_1_3_4_72_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99259-4_22"},{"key":"e_1_3_4_73_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0065-2458(08)60520-3"},{"key":"e_1_3_4_74_1","volume-title":"International Conference on AI and OR Techniques in Constraint Programming for Combinatorial Optimization Problems","author":"Sabharwal Ashish","year":"2017","unstructured":"Ashish Sabharwal, Horst Samulowitz, and Chandra Reddy. 2017. Guiding combinatorial optimization with UCT. In Proceedings of theInternational Conference on AI and OR Techniques in Constraint Programming for Combinatorial Optimization Problems. Springer."},{"key":"e_1_3_4_75_1","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201922)","author":"Sakaue Shinsaku","year":"2022","unstructured":"Shinsaku Sakaue and Taihei Oki. 2022. Sample complexity of learning heuristic functions for greedy-best-first and A* search. In Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201922)."},{"key":"e_1_3_4_76_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(01)00159-X"},{"key":"e_1_3_4_77_1","volume-title":"Handbook of Market Design","author":"Sandholm Tuomas","year":"2013","unstructured":"Tuomas Sandholm. 2013. Very-large-scale generalized combinatorial multi-attribute auctions: Lessons from conducting $60 billion of sourcing. In Handbook of Market Design, Zvika Neeman, Alvin Roth, and Nir Vulkan (Eds.). Oxford University Press."},{"key":"e_1_3_4_78_1","doi-asserted-by":"publisher","DOI":"10.1007\/11672142_19"},{"key":"e_1_3_4_79_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"e_1_3_4_80_1","volume-title":"International Conference on Artificial Intelligence and Statistics (AISTATS\u201920)","author":"Sharma Dravyansh","year":"2020","unstructured":"Dravyansh Sharma, Maria-Florina Balcan, and Travis Dick. 2020. Learning piecewise Lipschitz functions in changing environments. In Proceedings of theInternational Conference on Artificial Intelligence and Statistics (AISTATS\u201920)."},{"key":"e_1_3_4_81_1","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201920)","author":"Song Jialin","year":"2020","unstructured":"Jialin Song, Ravi Lanka, Yisong Yue, and Bistra Dilkina. 2020. A general large neighborhood search framework for solving integer programs. In Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201920)."},{"key":"e_1_3_4_82_1","article-title":"Learning to search via retrospective imitation","author":"Song Jialin","year":"2018","unstructured":"Jialin Song, Ravi Lanka, Albert Zhao, Aadyot Bhatnagar, Yisong Yue, and Masahiro Ono. 2018. Learning to search via retrospective imitation. arXiv preprint arXiv:1804.00846 (2018).","journal-title":"arXiv preprint arXiv:1804.00846"},{"key":"e_1_3_4_83_1","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v31i1.16008"},{"key":"e_1_3_4_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/990308.990310"},{"key":"e_1_3_4_85_1","first-page":"1577","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201909)","author":"Streeter Matthew","year":"2009","unstructured":"Matthew Streeter and Daniel Golovin. 2009. An online algorithm for maximizing submodular functions. In Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS\u201909). 1577\u20131584."},{"key":"e_1_3_4_86_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI\u201907)","author":"Streeter Matthew","year":"2007","unstructured":"Matthew Streeter, Daniel Golovin, and Stephen F. Smith. 2007. Combining multiple heuristics online. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI\u201907)."},{"key":"e_1_3_4_87_1","article-title":"Reinforcement learning for integer programming: Learning to cut","author":"Tang Yunhao","year":"2020","unstructured":"Yunhao Tang, Shipra Agrawal, and Yuri Faenza. 2020. Reinforcement learning for integer programming: Learning to cut. In Proceedings of theInternational Conference on Machine Learning (ICML) (2020).","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"e_1_3_4_88_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML\u201918)","author":"Weisz Gell\u00e9rt","year":"2018","unstructured":"Gell\u00e9rt Weisz, Andr\u00e1s Gy\u00f6rgy, and Csaba Szepesv\u00e1ri. 2018. LeapsAndBounds: A method for approximately optimal algorithm configuration. In Proceedings of the International Conference on Machine Learning (ICML\u201918)."},{"key":"e_1_3_4_89_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML\u201919)","author":"Weisz Gell\u00e9rt","year":"2019","unstructured":"Gell\u00e9rt Weisz, Andr\u00e1s Gy\u00f6rgy, and Csaba Szepesv\u00e1ri. 2019. CapsAndRuns: An improved method for approximately optimal algorithm configuration. In Proceedings of the International Conference on Machine Learning (ICML\u201919)."},{"key":"e_1_3_4_90_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12211"},{"key":"e_1_3_4_91_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2490"},{"key":"e_1_3_4_92_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7565"},{"key":"e_1_3_4_93_1","volume-title":"Proceedings of the RCRA Workshop on Experimental Evaluation of Algorithms for Solving Problems with Combinatorial Explosion at the International Joint Conference on Artificial Intelligence (IJCAI\u201911)","author":"Xu Lin","year":"2011","unstructured":"Lin Xu, Frank Hutter, Holger H. Hoos, and Kevin Leyton-Brown. 2011. Hydra-MIP: Automated algorithm configuration and selection for mixed integer programming. In Proceedings of the RCRA Workshop on Experimental Evaluation of Algorithms for Solving Problems with Combinatorial Explosion at the International Joint Conference on Artificial Intelligence (IJCAI\u201911)."}],"container-title":["Journal of the ACM"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637840","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637840","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:49:18Z","timestamp":1750286958000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637840"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,10]]},"references-count":92,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,4,30]]}},"alternative-id":["10.1145\/3637840"],"URL":"https:\/\/doi.org\/10.1145\/3637840","relation":{},"ISSN":["0004-5411","1557-735X"],"issn-type":[{"value":"0004-5411","type":"print"},{"value":"1557-735X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,10]]},"assertion":[{"value":"2020-10-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-09-28","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}