{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T06:45:25Z","timestamp":1773384325019,"version":"3.50.1"},"publisher-location":"Cham","reference-count":89,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031606014","type":"print"},{"value":"9783031605994","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-60599-4_14","type":"book-chapter","created":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T09:02:09Z","timestamp":1716800529000},"page":"221-233","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Optimization over\u00a0Trained Neural Networks: Taking a\u00a0Relaxing Walk"],"prefix":"10.1007","author":[{"given":"Jiatai","family":"Tong","sequence":"first","affiliation":[]},{"given":"Junyang","family":"Cai","sequence":"additional","affiliation":[]},{"given":"Thiago","family":"Serra","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,5,25]]},"reference":[{"key":"14_CR1","unstructured":"Dash, S., G\u00fcnl\u00fck, O., Wei, D.: Boolean decision rules via column generation. Neural Information Processing Systems (NeurIPS) (2018)"},{"key":"14_CR2","unstructured":"Aghaei, S., G\u00f3mez, A., Vayanos, P.: Strong optimal classification trees. arXiv:2103.15965 (2021)"},{"key":"14_CR3","unstructured":"Alston, B., Validi, H., Hicks, I.V.: Mixed integer linear optimization formulations for learning optimal binary classification trees. arXiv:2206.04857 (2022)"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Anderson, R., Huchette, J., Tjandraatmadja, C., Vielma, J.: Strong mixed-integer programming formulations for trained neural networks. In: Integer Programming and Combinatorial Optimization (IPCO) (2019)","DOI":"10.1007\/978-3-030-17953-3_3"},{"key":"14_CR5","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, J.P.: Strong mixed-integer programming formulations for trained neural networks. Math. Program. 183, 3\u201339 (2020)","journal-title":"Math. Program."},{"key":"14_CR6","unstructured":"Arora, R., Basu, A., Mianjy, P., Mukherjee, A.: Understanding deep neural networks with rectified linear units. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Aspman, J., Korpas, G., Marecek, J.: Taming binarized neural networks and mixed-integer programs. arXiv:2310.04469 (2023)","DOI":"10.1609\/aaai.v38i10.28968"},{"key":"14_CR8","unstructured":"Badilla, F., Goycoolea, M., Mu\u00f1oz, G., Serra, T.: Computational tradeoffs of optimization-based bound tightening in ReLU networks (2023)"},{"key":"14_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00148-3","volume-title":"Disjunctive Programming","author":"E Balas","year":"2018","unstructured":"Balas, E.: Disjunctive Programming. Springer, Cham (2018)"},{"key":"14_CR10","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1287\/ijoc.2020.1023","volume":"34","author":"D Bergman","year":"2022","unstructured":"Bergman, D., Huang, T., Brooks, P., Lodi, A., Raghunathan, A.U.: JANOS: an integrated predictive and prescriptive modeling framework. INFORMS J. Comput. 34, 807\u2013816 (2022)","journal-title":"INFORMS J. Comput."},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Bernardelli, A.M., Gualandi, S., Lau, H.C., Milanesi, S.: The BeMi stardust: a structured ensemble of binarized neural networks. In: Learning and Intelligent Optimization (LION) (2023)","DOI":"10.1007\/978-3-031-44505-7_30"},{"key":"14_CR12","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1007\/s10994-017-5633-9","volume":"106","author":"D Bertsimas","year":"2017","unstructured":"Bertsimas, D., Dunn, J.: Optimal classification trees. Mach. Learn. 106, 1039\u20131082 (2017)","journal-title":"Mach. Learn."},{"key":"14_CR13","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1287\/opre.1060.0360","volume":"55","author":"D Bertsimas","year":"2007","unstructured":"Bertsimas, D., Shioda, R.: Classification and regression via integer optimization. Oper. Res. 55, 252\u2013271 (2007)","journal-title":"Oper. Res."},{"key":"14_CR14","doi-asserted-by":"publisher","first-page":"100795","DOI":"10.1016\/j.disopt.2023.100795","volume":"49","author":"D Bienstock","year":"2023","unstructured":"Bienstock, D., Mu\u00f1oz, G., Pokutta, S.: Principled deep neural network training through linear programming. Discrete Optim. 49, 100795 (2023)","journal-title":"Discrete Optim."},{"key":"14_CR15","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/s10107-015-0891-4","volume":"151","author":"P Bonami","year":"2015","unstructured":"Bonami, P., Lodi, A., Tramontani, A., Wiese, S.: On mathematical programming with indicator constraints. Math. Program. 151, 191\u2013223 (2015)","journal-title":"Math. Program."},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Botoeva, E., Kouvaros, P., Kronqvist, J., Lomuscio, A., Misener, R.: Efficient verification of relu-based neural networks via dependency analysis. In: AAAI Conference on Artificial Intelligence (AAAI) (2020)","DOI":"10.1609\/aaai.v34i04.5729"},{"key":"14_CR17","series-title":"NATO ASI Series","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/978-3-642-76153-9_28","volume-title":"Neurocomputing","author":"JS Bridle","year":"1990","unstructured":"Bridle, J.S.: Probabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition. In: Souli\u00e9, F.F., H\u00e9rault, J. (eds.) Neurocomputing. NATO ASI Series, vol. 68, pp. 227\u2013236. Springer, Heidelberg (1990). https:\/\/doi.org\/10.1007\/978-3-642-76153-9_28"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Burtea, R.A., Tsay, C.: Safe deployment of reinforcement learning using deterministic optimization over neural networks. In: Computer Aided Chemical Engineering, vol.\u00a052, pp. 1643\u20131648. Elsevier (2023)","DOI":"10.1016\/B978-0-443-15274-0.50261-4"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Cacciola, M., Frangioni, A., Lodi, A.: Structured pruning of neural networks for constraints learning. arXiv:2307.07457 (2023)","DOI":"10.1016\/j.orl.2024.107194"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Cai, J., et al.: Getting away with more network pruning: from sparsity to geometry and linear regions. In: International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR) (2023)","DOI":"10.1007\/978-3-031-33271-5_14"},{"key":"14_CR21","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s11750-021-00594-1","volume":"29","author":"E Carrizosa","year":"2021","unstructured":"Carrizosa, E., Molero-R\u00edo, C., Morales, D.R.: Mathematical optimization in classification and regression trees. TOP 29, 5\u201333 (2021)","journal-title":"TOP"},{"issue":"349","key":"14_CR22","first-page":"1","volume":"23","author":"F Ceccon","year":"2022","unstructured":"Ceccon, F., et al.: Omlt: optimization & machine learning toolkit. J. Mach. Learn. Res. 23(349), 1\u20138 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"14_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2020.106741","volume":"189","author":"Y Chen","year":"2020","unstructured":"Chen, Y., Shi, Y., Zhang, B.: Data-driven optimal voltage regulation using input convex neural networks. Electr. Power Syst. Res. 189, 106741 (2020)","journal-title":"Electr. Power Syst. Res."},{"key":"14_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-319-68167-2_18","volume-title":"Automated Technology for Verification and Analysis","author":"C-H Cheng","year":"2017","unstructured":"Cheng, C.-H., N\u00fchrenberg, G., Ruess, H.: Maximum resilience of artificial neural networks. In: D\u2019Souza, D., Narayan Kumar, K. (eds.) ATVA 2017. LNCS, vol. 10482, pp. 251\u2013268. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-68167-2_18"},{"key":"14_CR25","series-title":"Graduate Texts in Mathematics","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1007\/978-3-319-11008-0_7","volume-title":"Integer Programming","author":"M Conforti","year":"2014","unstructured":"Conforti, M., Cornu\u00e9jols, G., Zambelli, G.: Valid inequalities for structured integer programs. In: Integer Programming. GTM, vol. 271, pp. 281\u2013319. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-11008-0_7"},{"key":"14_CR26","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/BF02551274","volume":"2","author":"G Cybenko","year":"1989","unstructured":"Cybenko, G.: Approximation by superpositions of a sigmoidal function. Math. Control, Signals Syst. 2, 303\u2013314 (1989)","journal-title":"Math. Control, Signals Syst."},{"key":"14_CR27","unstructured":"Delarue, A., Anderson, R., Tjandraatmadja, C.: Reinforcement learning with combinatorial actions: an application to vehicle routing. In: NeurIPS (2020)"},{"key":"14_CR28","first-page":"1","volume":"23","author":"E Demirovi\u0107","year":"2022","unstructured":"Demirovi\u0107, E., et al.: MurTree: optimal decision trees via dynamic programming and search. J. Mach. Learn. Res. 23, 1\u201347 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"14_CR29","unstructured":"Dumouchelle, J., Julien, E., Kurtz, J., Khalil, E.B.: Neur2RO: neural two-stage robust optimization. arXiv:2310.04345 (2023)"},{"key":"14_CR30","unstructured":"Dumouchelle, J., Patel, R., Khalil, E.B., Bodur, M.: Neur2SP: neural two-stage stochastic programming. In: Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"14_CR31","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/978-3-031-33271-5_15","volume-title":"Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR)","author":"M ElAraby","year":"2023","unstructured":"ElAraby, M., Wolf, G., Carvalho, M.: OAMIP: optimizing ANN architectures using mixed-integer programming. In: Cire, A.A. (ed.) Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR). LNCS, vol. 13884, pp. 219\u2013237. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-33271-5_15"},{"key":"14_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ejor.2023.04.041","volume":"314","author":"A Fajemisin","year":"2023","unstructured":"Fajemisin, A., Maragno, D., den Hertog, D.: Optimization with constraint learning: a framework and survey. Eur. J. Oper. Res. 314, 1\u201314 (2023)","journal-title":"Eur. J. Oper. Res."},{"key":"14_CR33","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.: Deep neural networks and mixed integer linear optimization. Constraints 23, 296\u2013309 (2018)","journal-title":"Constraints"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Florio, A.M., Martins, P., Schiffer, M., Serra, T., Vidal, T.: Optimal decision diagrams for classification. In: AAAI Conference on Artificial Intelligence (AAAI) (2023)","DOI":"10.1609\/aaai.v37i6.25920"},{"key":"14_CR35","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/0893-6080(89)90003-8","volume":"2","author":"KI Funahashi","year":"1989","unstructured":"Funahashi, K.I.: On the approximate realization of continuous mappings by neural networks. Neural Netw. 2, 183\u2013192 (1989)","journal-title":"Neural Netw."},{"key":"14_CR36","unstructured":"Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: International Conference on Artificial Intelligence and Statistics (AISTATS) (2011)"},{"key":"14_CR37","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/s10898-021-01009-y","volume":"81","author":"O G\u00fcnl\u00fck","year":"2021","unstructured":"G\u00fcnl\u00fck, O., Kalagnanam, J., Li, M., Menickelly, M., Scheinberg, K.: Optimal decision trees for categorical data via integer programming. J. Global Optim. 81, 233\u2013260 (2021)","journal-title":"J. Global Optim."},{"key":"14_CR38","unstructured":"Gurobi: Gurobi Machine Learning (2023). https:\/\/github.com\/Gurobi\/gurobi-machinelearning. Accessed 03 Dec 2023"},{"key":"14_CR39","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1038\/35016072","volume":"405","author":"R Hahnloser","year":"2000","unstructured":"Hahnloser, R., Sarpeshkar, R., Mahowald, M., Douglas, R., Seung, S.: Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit. Nature 405, 947\u2013951 (2000)","journal-title":"Nature"},{"key":"14_CR40","unstructured":"Hanin, B., Rolnick, D.: Complexity of linear regions in deep networks. In: International Conference on Machine Learning (ICML) (2019)"},{"key":"14_CR41","unstructured":"Hanin, B., Rolnick, D.: Deep ReLU networks have surprisingly few activation patterns. In: Neural Information Processing Systems (NeurIPS), vol.\u00a032 (2019)"},{"key":"14_CR42","unstructured":"Hanin, B., Sellke, M.: Approximating continuous functions by ReLU nets of minimal width. arXiv:1710.11278 (2017)"},{"key":"14_CR43","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","volume":"2","author":"K Hornik","year":"1989","unstructured":"Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2, 359\u2013366 (1989)","journal-title":"Neural Netw."},{"key":"14_CR44","doi-asserted-by":"crossref","unstructured":"Hu, H., Huguet, M.J., Siala, M.: Optimizing binary decision diagrams with maxsat for classification. In: AAAI Conference on Artificial Intelligence (AAAI) (2022)","DOI":"10.1609\/aaai.v36i4.20291"},{"key":"14_CR45","unstructured":"Hu, X., Rudin, C., Seltzer, M.: Optimal sparse decision trees. In: Neural Information Processing Systems (NeurIPS) (2019)"},{"key":"14_CR46","unstructured":"Huchette, J., Mu\u00f1oz, G., Serra, T., Tsay, C.: When deep learning meets polyhedral theory: a survey. arXiv:2305.00241 (2023)"},{"key":"14_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1007\/978-3-030-30048-7_24","volume-title":"Principles and Practice of Constraint Programming","author":"R Toro Icarte","year":"2019","unstructured":"Toro Icarte, R., Illanes, L., Castro, M.P., Cire, A.A., McIlraith, S.A., Beck, J.C.: Training binarized neural networks using MIP and CP. In: Schiex, T., de Givry, S. (eds.) CP 2019. LNCS, vol. 11802, pp. 401\u2013417. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30048-7_24"},{"key":"14_CR48","doi-asserted-by":"crossref","unstructured":"Kanamori, K., Takagi, T., Kobayashi, K., Ike, Y., Uemura, K., Arimura, H.: Ordered counterfactual explanation by mixed-integer linear optimization. In: AAAI Conference on Artificial Intelligence (AAAI) (2021)","DOI":"10.24963\/ijcai.2020\/395"},{"key":"14_CR49","doi-asserted-by":"crossref","unstructured":"Kronqvist, J., Li, B., Rolfes, J., Zhao, S.: Alternating mixed-integer programming and neural network training for approximating stochastic two-stage problems. arXiv:2305.06785 (2023)","DOI":"10.1007\/978-3-031-53966-4_10"},{"key":"14_CR50","unstructured":"Kurtz, J., Bah, B.: Efficient and robust mixed-integer optimization methods for training binarized deep neural networks. arXiv:2110.11382 (2021)"},{"issue":"229","key":"14_CR51","first-page":"1","volume":"24","author":"C Lawless","year":"2023","unstructured":"Lawless, C., Dash, S., G\u00fcnl\u00fck, O., Wei, D.: Interpretable and fair Boolean rule sets via column generation. J. Mach. Learn. Res. 24(229), 1\u201350 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"14_CR52","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. In: Proceedings of the IEEE (1998)","DOI":"10.1109\/5.726791"},{"key":"14_CR53","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436\u2013444 (2015)","journal-title":"Nature"},{"key":"14_CR54","doi-asserted-by":"crossref","unstructured":"Liu, C., Arnon, T., Lazarus, C., Strong, C., Barrett, C., Kochenderfer, M.J., et\u00a0al.: Algorithms for verifying deep neural networks. Found. Trends\u00ae Optim. 4(3-4), 244\u2013404 (2021)","DOI":"10.1561\/2400000035"},{"key":"14_CR55","unstructured":"Lu, Z., Pu, H., Wang, F., Hu, Z., Wang, L.: The expressive power of neural networks: a view from the width. In: Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"14_CR56","doi-asserted-by":"crossref","unstructured":"Maragno, D., Wiberg, H., Bertsimas, D., Birbil, S.I., Hertog, D.d., Fajemisin, A.: Mixed-integer optimization with constraint learning. Oper. Res. (2023)","DOI":"10.1287\/opre.2021.0707"},{"key":"14_CR57","doi-asserted-by":"crossref","unstructured":"McDonald, T., Tsay, C., Schweidtmann, A.M., Yorke-Smith, N.: Mixed-integer optimisation of graph neural networks for computer-aided molecular design. arXiv:2312.01228 (2023)","DOI":"10.1016\/j.compchemeng.2024.108660"},{"key":"14_CR58","unstructured":"Mont\u00fafar, G.: Notes on the number of linear regions of deep neural networks. In: Sampling Theory and Applications (SampTA) (2017)"},{"key":"14_CR59","unstructured":"Mont\u00fafar, G., Pascanu, R., Cho, K., Bengio, Y.: On the number of linear regions of deep neural networks. In: Neural Information Processing Systems (NeurIPS), vol.\u00a027 (2014)"},{"key":"14_CR60","unstructured":"Murzakhanov, I., Venzke, A., Misyris, G.S., Chatzivasileiadis, S.: Neural networks for encoding dynamic security-constrained optimal power flow. In: Bulk Power Systems Dynamics and Control Symposium (2022)"},{"key":"14_CR61","unstructured":"Nair, V., Hinton, G.: Rectified linear units improve restricted Boltzmann machines. In: International Conference on Machine Learning (ICML) (2010)"},{"key":"14_CR62","unstructured":"Park, S., Yun, C., Lee, J., Shin, J.: Minimum width for universal approximation. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"14_CR63","unstructured":"Pascanu, R., Mont\u00fafar, G., Bengio, Y.: On the number of response regions of deep feedforward networks with piecewise linear activations. In: International Conference on Learning Representations (ICLR) (2014)"},{"key":"14_CR64","unstructured":"Patil, V., Mintz, Y.: A mixed-integer programming approach to training dense neural networks. arXiv:2201.00723 (2022)"},{"key":"14_CR65","unstructured":"Perakis, G., Tsiourvas, A.: Optimizing objective functions from trained ReLU neural networks via sampling. arXiv:2205.14189 (2022)"},{"key":"14_CR66","unstructured":"Raghu, M., Poole, B., Kleinberg, J., Ganguli, S., Dickstein, J.: On the expressive power of deep neural networks. In: International Conference on Machine Learning (ICML) (2017)"},{"key":"14_CR67","unstructured":"Ramachandran, P., Zoph, B., Le, Q.V.: Searching for activation functions. In: ICLR Workshop Track (2018)"},{"key":"14_CR68","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1007\/978-3-031-26419-1_21","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"B Rosenhahn","year":"2022","unstructured":"Rosenhahn, B.: Mixed integer linear programming for optimizing a hopfield network. In: Amini, M.R., Canu, S., Fischer, A., Guns, T., Kralj Novak, P., Tsoumakas, G. (eds.) ECML PKDD. LNCS, vol. 13717, pp. 344\u2013360. Springer, Cham (2022)"},{"key":"14_CR69","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s10898-020-00949-1","volume":"81","author":"A R\u00f6ssig","year":"2021","unstructured":"R\u00f6ssig, A., Petkovic, M.: Advances in verification of ReLU neural networks. J. Global Optim. 81, 109\u2013152 (2021)","journal-title":"J. Global Optim."},{"key":"14_CR70","doi-asserted-by":"crossref","unstructured":"Say, B., Wu, G., Zhou, Y.Q., Sanner, S.: Nonlinear hybrid planning with deep net learned transition models and mixed-integer linear programming. In: International Joint Conference on Artificial Intelligence (IJCAI) (2017)","DOI":"10.24963\/ijcai.2017\/104"},{"key":"14_CR71","doi-asserted-by":"crossref","unstructured":"Serra, T., Ramalingam, S.: Empirical bounds on linear regions of deep rectifier networks. In: AAAI Conference on Artificial Intelligence (AAAI) (2020)","DOI":"10.1609\/aaai.v34i04.6016"},{"key":"14_CR72","unstructured":"Serra, T., Tjandraatmadja, C., Ramalingam, S.: Bounding and counting linear regions of deep neural networks. In: International Conference on Machine Learning (ICML) (2018)"},{"key":"14_CR73","unstructured":"Serra, T., Yu, X., Kumar, A., Ramalingam, S.: Scaling up exact neural network compression by ReLU stability. In: Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"14_CR74","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/978-3-030-58942-4_27","volume-title":"Integration of Constraint Programming, Artificial Intelligence, and Operations Research","author":"T Serra","year":"2020","unstructured":"Serra, T., Kumar, A., Ramalingam, S.: Lossless compression of deep neural networks. In: Hebrard, E., Musliu, N. (eds.) CPAIOR 2020. LNCS, vol. 12296, pp. 417\u2013430. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58942-4_27"},{"key":"14_CR75","doi-asserted-by":"publisher","first-page":"3685","DOI":"10.1007\/s10994-021-06050-2","volume":"112","author":"CA Strong","year":"2021","unstructured":"Strong, C.A., Wu, H., Zelji\u0107, A., Julian, K.D., Katz, G., Barrett, C., Kochenderfer, M.J.: Global optimization of objective functions represented by ReLU networks. Mach. Learn. 112, 3685\u20133712 (2021)","journal-title":"Mach. Learn."},{"key":"14_CR76","unstructured":"Telgarsky, M.: Representation benefits of deep feedforward networks. arXiv:1509.08101 (2015)"},{"key":"14_CR77","doi-asserted-by":"publisher","first-page":"e0261029","DOI":"10.1371\/journal.pone.0261029","volume":"18","author":"T Thorbjarnarson","year":"2023","unstructured":"Thorbjarnarson, T., Yorke-Smith, N.: Optimal training of integer-valued neural networks with mixed integer programming. PLoS ONE 18, e0261029 (2023)","journal-title":"PLoS ONE"},{"key":"14_CR78","unstructured":"Tjeng, V., Xiao, K., Tedrake, R.: Evaluating robustness of neural networks with mixed integer programming. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"14_CR79","unstructured":"Tong, J., Cai, J., Serra, T.: Relax-and-Walk Implementation (2024). https:\/\/github.com\/JiataiTong\/Optimization-Over-Trained-Neural-Networks-Taking-a-Relaxing-Walk. Accessed 28 Jan 2024"},{"key":"14_CR80","unstructured":"Tsay, C., Kronqvist, J., Thebelt, A., Misener, R.: Partition-based formulations for mixed-integer optimization of trained ReLU neural networks. In: Neural Information Processing Systems (NeurIPS), vol.\u00a034 (2021)"},{"key":"14_CR81","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1007\/s10601-020-09312-3","volume":"25","author":"H Verhaeghe","year":"2020","unstructured":"Verhaeghe, H., Nijssen, S., Pesant, G., Quimper, C.G., Schaus, P.: Learning optimal decision trees using constraint programming. Constraints 25, 226\u2013250 (2020)","journal-title":"Constraints"},{"key":"14_CR82","doi-asserted-by":"crossref","unstructured":"Verwer, S., Zhang, Y.: Learning decision trees with flexible constraints and objectives using integer optimization. In: International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR) (2017)","DOI":"10.1007\/978-3-319-59776-8_8"},{"key":"14_CR83","doi-asserted-by":"crossref","unstructured":"Verwer, S., Zhang, Y.: Learning optimal classification trees using a binary linear program formulation. In: AAAI Conference on Artificial Intelligence (AAAI) (2019)","DOI":"10.1609\/aaai.v33i01.33011624"},{"key":"14_CR84","doi-asserted-by":"crossref","unstructured":"Wang, Y.: Estimation and comparison of linear regions for ReLU networks. In: International Joint Conference on Artificial Intelligence (IJCAI) (2022)","DOI":"10.24963\/ijcai.2022\/492"},{"key":"14_CR85","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1613\/jair.1.11829","volume":"68","author":"G Wu","year":"2020","unstructured":"Wu, G., Say, B., Sanner, S.: Scalable planning with deep neural network learned transition models. J. Artif. Intell. Res. 68, 571\u2013606 (2020)","journal-title":"J. Artif. Intell. Res."},{"key":"14_CR86","unstructured":"Xiao, K.Y., Tjeng, V., Shafiullah, N.M., Madry, A.: Training for faster adversarial robustness verification via inducing ReLU stability. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"14_CR87","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2020.107143","volume":"144","author":"S Yang","year":"2021","unstructured":"Yang, S., Bequette, B.W.: Optimization-based control using input convex neural networks. Comput. Chem. Eng. 144, 107143 (2021)","journal-title":"Comput. Chem. Eng."},{"key":"14_CR88","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.neunet.2017.07.002","volume":"94","author":"D Yarotsky","year":"2017","unstructured":"Yarotsky, D.: Error bounds for approximations with deep ReLU networks. Neural Netw. 94, 103\u2013114 (2017)","journal-title":"Neural Netw."},{"key":"14_CR89","unstructured":"Zhu, H., Murali, P., Phan, D., Nguyen, L., Kalagnanam, J.: A scalable MIP-based method for learning optimal multivariate decision trees. In: Neural Information Processing Systems (NeurIPS) (2020)"}],"container-title":["Lecture Notes in Computer Science","Integration of Constraint Programming, Artificial Intelligence, and Operations Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-60599-4_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T02:24:40Z","timestamp":1732069480000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-60599-4_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031606014","9783031605994"],"references-count":89,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-60599-4_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"25 May 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CPAIOR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Uppsala","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 May 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 May 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cpaior2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sites.google.com\/view\/cpaior2024","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}