{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:44:31Z","timestamp":1781279071824,"version":"3.54.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,2,8]],"date-time":"2025-02-08T00:00:00Z","timestamp":1738972800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,8]],"date-time":"2025-02-08T00:00:00Z","timestamp":1738972800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Engineering with Computers"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s00366-025-02114-2","type":"journal-article","created":{"date-parts":[[2025,2,8]],"date-time":"2025-02-08T14:48:27Z","timestamp":1739026107000},"page":"2411-2429","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Feed-forward neural networks as a mixed-integer program"],"prefix":"10.1007","volume":"41","author":[{"given":"Navid","family":"Aftabi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nima","family":"Moradi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fatemeh","family":"Mahroo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,2,8]]},"reference":[{"issue":"6245","key":"2114_CR1","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1126\/science.aaa8415","volume":"349","author":"MI Jordan","year":"2015","unstructured":"Jordan MI, Mitchell TM (2015) Machine learning: trends, perspectives, and prospects. Science 349(6245):255\u2013260","journal-title":"Science"},{"issue":"49","key":"2114_CR2","first-page":"1","volume":"24","author":"M Agarwal","year":"2023","unstructured":"Agarwal M, Aggarwal V (2023) Reinforcement learning for joint optimization of multiple rewards. J Mach Learn Res 24(49):1\u201341","journal-title":"J Mach Learn Res"},{"key":"2114_CR3","volume-title":"What is machine learning?","author":"I El Naqa","year":"2015","unstructured":"El Naqa I, Murphy MJ (2015) What is machine learning? Springer, Cham"},{"key":"2114_CR4","first-page":"1265","volume":"7","author":"KP Bennett","year":"2006","unstructured":"Bennett KP, Parrado-Hern\u00e1ndez E (2006) The interplay of optimization and machine learning research. J Mach Learn Res 7:1265\u20131281","journal-title":"J Mach Learn Res"},{"key":"2114_CR5","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1016\/j.ejor.2020.08.045","volume":"290","author":"C Gambella","year":"2020","unstructured":"Gambella C, Ghaddar B, Naoum-Sawaya J (2020) Optimization problems for machine learning: a survey. Eur J Oper Res 290:807\u2013828","journal-title":"Eur J Oper Res"},{"issue":"2","key":"2114_CR6","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1137\/16M1080173","volume":"60","author":"L Bottou","year":"2018","unstructured":"Bottou L, Curtis FE, Nocedal J (2018) Optimization methods for large-scale machine learning. SIAM Rev 60(2):223\u2013311","journal-title":"SIAM Rev"},{"key":"2114_CR7","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A, Bengio Y (2016) Deep learning, vol 1. MIT Press, Cambridge"},{"key":"2114_CR8","volume-title":"Machine learning under a modern optimization lens","author":"D Bertsimas","year":"2019","unstructured":"Bertsimas D, Dunn J (2019) Machine learning under a modern optimization lens. Dynamic Ideas LLC, Charlestown"},{"key":"2114_CR9","volume-title":"Integer and combinatorial optimization","author":"LA Wolsey","year":"2014","unstructured":"Wolsey LA, Nemhauser GL (2014) Integer and combinatorial optimization. Wiley, Hoboken"},{"key":"2114_CR10","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10107-020-01474-5","volume":"183","author":"R Anderson","year":"2020","unstructured":"Anderson R, Huchette J, Ma W, Tjandraatmadja C, Vielma JP (2020) Strong mixed-integer programming formulations for trained neural networks. Math Program 183:3\u201339","journal-title":"Math Program"},{"key":"2114_CR11","first-page":"89","volume-title":"Leading developments from INFORMS communities","author":"FE Curtis","year":"2017","unstructured":"Curtis FE, Scheinberg K (2017) Optimization methods for supervised machine learning: from linear models to deep learning. Leading developments from INFORMS communities. INFORMS, Catonsville, pp 89\u2013114"},{"issue":"2","key":"2114_CR12","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1016\/j.ejor.2020.07.063","volume":"290","author":"Y Bengio","year":"2021","unstructured":"Bengio Y, Lodi A, Prouvost A (2021) Machine learning for combinatorial optimization: a methodological tour d\u2019horizon. Eur J Oper Res 290(2):405\u2013421","journal-title":"Eur J Oper Res"},{"issue":"3\u20134","key":"2114_CR13","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1561\/2400000035","volume":"4","author":"C Liu","year":"2021","unstructured":"Liu C, Arnon T, Lazarus C, Strong C, Barrett C, Kochenderfer MJ et al (2021) Algorithms for verifying deep neural networks. Found Trends Optim 4(3\u20134):244\u2013404","journal-title":"Found Trends Optim"},{"issue":"12","key":"2114_CR14","first-page":"1987","volume":"2","author":"C Maureen","year":"1989","unstructured":"Maureen C, Caudill M (1989) Neural network primer: part I. AI Expert 2(12):1987","journal-title":"AI Expert"},{"issue":"59","key":"2114_CR15","first-page":"1","volume":"24","author":"ER Love","year":"2023","unstructured":"Love ER, Filippenko B, Maroulas V, Carlsson G (2023) Topological convolutional layers for deep learning. J Mach Learn Res 24(59):1\u201335","journal-title":"J Mach Learn Res"},{"issue":"1","key":"2114_CR16","first-page":"2157","volume":"22","author":"SH Lim","year":"2021","unstructured":"Lim SH (2021) Understanding recurrent neural networks using nonequilibrium response theory. J Mach Learn Res 22(1):2157\u20132204","journal-title":"J Mach Learn Res"},{"issue":"42","key":"2114_CR17","first-page":"1","volume":"23","author":"Z Li","year":"2022","unstructured":"Li Z, Han J, Weinan E, Li Q (2022) Approximation and optimization theory for linear continuous-time recurrent neural networks. J Mach Learn Res 23(42):1\u201385","journal-title":"J Mach Learn Res"},{"key":"2114_CR18","unstructured":"Bunel RR, Turkaslan I, Torr P, Kohli P, Mudigonda PK (2018) A unified view of piecewise linear neural network verification. In: Advances in neural information processing systems 31"},{"key":"2114_CR19","doi-asserted-by":"crossref","unstructured":"Cheng C-H, N\u00fchrenberg G, Ruess H (2017) Maximum resilience of artificial neural networks. In: International symposium on automated technology for verification and analysis. Springer, pp 251\u2013268","DOI":"10.1007\/978-3-319-68167-2_18"},{"key":"2114_CR20","unstructured":"Lomuscio A, Maganti L (2017) An approach to reachability analysis for feed-forward RELU neural networks. arXiv preprint arXiv:1706.07351"},{"key":"2114_CR21","unstructured":"Tjeng V, Xiao KY, Tedrake R (2018) Evaluating robustness of neural networks with mixed integer programming. In: International conference on learning representations"},{"issue":"42","key":"2114_CR22","first-page":"1","volume":"21","author":"R Bunel","year":"2020","unstructured":"Bunel R, Lu J, Turkaslan I, Torr PH, Kohli P, Kumar MP (2020) Branch and bound for piecewise linear neural network verification. J Mach Learn Res 21(42):1\u201339","journal-title":"J Mach Learn Res"},{"key":"2114_CR23","doi-asserted-by":"crossref","unstructured":"Dutta S, Jha S, Sanakaranarayanan S, Tiwari A (2017) Output range analysis for deep neural networks. arXiv preprint arXiv:1709.09130","DOI":"10.1007\/978-3-319-77935-5_9"},{"key":"2114_CR24","unstructured":"Serra T, Tjandraatmadja C, Ramalingam S (2018) Bounding and counting linear regions of deep neural networks. In: International conference on machine learning. PMLR, pp. 4558\u20134566"},{"key":"2114_CR25","first-page":"5628","volume":"34","author":"T Serra","year":"2020","unstructured":"Serra T, Ramalingam S (2020) Empirical bounds on linear regions of deep rectifier networks. Proc AAAI Conf Artif Intell 34:5628\u20135635","journal-title":"Proc AAAI Conf Artif Intell"},{"issue":"3","key":"2114_CR26","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1007\/s10601-018-9285-6","volume":"23","author":"M Fischetti","year":"2018","unstructured":"Fischetti M, Jo J (2018) Deep neural networks and mixed integer linear optimization. Constraints 23(3):296\u2013309","journal-title":"Constraints"},{"key":"2114_CR27","unstructured":"ElAraby M, Wolf G, Carvalho M (2020) Identifying critical neurons in ANN architectures using mixed integer programming. arXiv preprint arXiv:2002.07259"},{"key":"2114_CR28","unstructured":"Carrasco P, Mu\u00f1oz G (2024) Tightening convex relaxations of trained neural networks: a unified approach for convex and S-shaped activations. https:\/\/arxiv.org\/abs\/2410.23362"},{"key":"2114_CR29","unstructured":"Kumar A, Serra T, Ramalingam S (2019) Equivalent and approximate transformations of deep neural networks. arXiv preprint arXiv:1905.11428"},{"key":"2114_CR30","first-page":"3068","volume":"34","author":"C Tsay","year":"2021","unstructured":"Tsay C, Kronqvist J, Thebelt A, Misener R (2021) Partition-based formulations for mixed-integer optimization of trained RELU neural networks. Adv Neural Inf Process Syst 34:3068\u20133080","journal-title":"Adv Neural Inf Process Syst"},{"key":"2114_CR31","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/978-3-030-78230-6_19","volume-title":"Integration of constraint programming, artificial intelligence, and operations research","author":"J Kronqvist","year":"2021","unstructured":"Kronqvist J, Misener R, Tsay C (2021) Between steps: intermediate relaxations between big-m and convex hull formulations. In: Stuckey PJ (ed) Integration of constraint programming, artificial intelligence, and operations research. Springer, Cham, pp 299\u2013314"},{"issue":"POPL","key":"2114_CR32","doi-asserted-by":"publisher","first-page":"2260","DOI":"10.1145\/3632917","volume":"8","author":"Z Ma","year":"2024","unstructured":"Ma Z, Li J, Bai G (2024) RELU hull approximation. Proc ACM Program Lang 8(POPL):2260\u20132287. https:\/\/doi.org\/10.1145\/3632917","journal-title":"Proc ACM Program Lang"},{"key":"2114_CR33","unstructured":"Wilson AC, Roelofs R, Stern M, Srebro N, Recht B (2017) The marginal value of adaptive gradient methods in machine learning. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R (eds) Advances in neural information processing systems, vol 30. Curran Associates, Inc., New York. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/81b3833e2504647f9d794f7d7b9bf341-Paper.pdf"},{"key":"2114_CR34","unstructured":"Bah B, Kurtz J (2020) An integer programming approach to deep neural networks with binary activation functions. arXiv preprint arXiv:2007.03326"},{"key":"2114_CR35","unstructured":"\u00deorbjarnarson T, Yorke-Smith N (2021) On training neural networks with mixed integer programming. In: IJCAI-PRICAI\u201920 workshop on data science meets optimisation"},{"key":"2114_CR36","doi-asserted-by":"crossref","unstructured":"Icarte RT, Illanes L, Castro MP, Cire AA, McIlraith SA, Beck JC (2019) Training binarized neural networks using MIP and CP. In: International conference on principles and practice of constraint programming. Springer, pp. 401\u2013417","DOI":"10.1007\/978-3-030-30048-7_24"},{"key":"2114_CR37","unstructured":"Hubara I, Courbariaux M, Soudry D, El-Yaniv R, Bengio Y (2016) Binarized neural networks. In: Proceedings of the 30th international conference on neural information processing systems, pp 4114\u20134122"},{"issue":"11","key":"2114_CR38","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"},{"key":"2114_CR39","unstructured":"Abadi M (2016) Tensorflow: large-scale machine learning on heterogeneous distributed systems. CoRR"},{"key":"2114_CR40","unstructured":"Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow I, Fergus R (2014) Intriguing properties of neural networks. In: 2nd International conference on learning representations, ICLR 2014"},{"key":"2114_CR41","unstructured":"Zhao WX, Zhou K, Li J, Tang T, Wang X, Hou Y, Min Y, Zhang B, Zhang J, Dong Z, Du Y, Yang C, Chen Y, Chen Z, Jiang J, Ren R, Li Y, Tang X, Liu Z, Liu P, Nie J-Y, Wen J-R (2024) A survey of large language models. https:\/\/arxiv.org\/abs\/2303.18223"},{"key":"2114_CR42","doi-asserted-by":"publisher","unstructured":"Khaniyev T, Copenhaver MS, Safavi KC, Zenteno\u00a0Langle AC, Starobinski KS, Daily B, Dunn P, Levi R (2024) A prescriptive optimization approach to identification of minimal barriers for surgical patients. medRxiv https:\/\/doi.org\/10.1101\/2023.03.24.23287694","DOI":"10.1101\/2023.03.24.23287694"}],"container-title":["Engineering with Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00366-025-02114-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00366-025-02114-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00366-025-02114-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T23:29:25Z","timestamp":1758065365000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00366-025-02114-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,8]]},"references-count":42,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["2114"],"URL":"https:\/\/doi.org\/10.1007\/s00366-025-02114-2","relation":{},"ISSN":["0177-0667","1435-5663"],"issn-type":[{"value":"0177-0667","type":"print"},{"value":"1435-5663","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,8]]},"assertion":[{"value":"7 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}