USING MACHINE LEARNING APPLICATIONS TO IMPROVE MATHEMATICAL OPTIMIZATION

Alina BABOȘ, Cristina BĂTUȘARU

Abstract


Inthis paper we want to demonstrate how an application of Machine Learning (regression) can be used to improve an optimization model (linear programming problem). We calculate the expected optimal number of enterprises engaged in e-sales in each country for 22 European countries using a linear programming problem, knowing their population, minimum wage on month and e-sales. We improve the optimization model by using the predicted e-sales obtained by regression

Full Text:

PDF

References


Chen, XH, Liu, JL, Yin, WT, Learning to optimize: A tutorial for continuous and mixed-integer optimization, Science China-Mathematics, 67(6), 2024 , pp.1191–1262.

https://doi.org/10.1007/s11425-023-2293-3.

Cengil, F, Nagarajan, H, Bent, R, Eksioglu, S, Eksioglu, B, Learning to accelerate tightening of convex relaxations of the AC optimal power flow problem, Computational Optimization and Applications, 92(3), 2025. 761–786, https://doi.org/10.1007/s10589-025-00715-7.

Mai, HT, Kang, J, Lee, J, A machine learning-based surrogate model for optimization, Finite Elements in Analysis and Design, 2021, 196, Article 103572,

https://doi.org/10.1016/j.finel.2021.103572.

Kim, SH, Boukouvala, F., Machine learning-based surrogate modeling for mathematical optimization, Mathematical Programming Computation, 14(4), 2020, pp. 989–1010. https://doi.org/10.1007/s11590-019-01428-7.

Müller, J, Park, J, Sahu, R, Varadharajan, C; Arora, B, Faybishenko, B, Wainwright, H, Surrogate optimization of deep neural networks for groundwater modeling, Journal of Global Optimization, 81(1), 2021, pp. 203–231,

https://doi.org/10.1007/s10898-020-00912-0.

Motoyama, Y, Tamura, R, Yoshimi, K, Terayama, K, Ueno, R, Tsuda, K, Bayesian optimization package for materials and physical sciences workflows, Computer Physics Communications, 278, 2022, Article 108405, https://doi.org/10.1016/j.cpc.2022.108405

Attia, A, Leyffer, S, Munson, TS, Stochastic learning approach for binary optimization: application to Bayesian optimal design of experiments, SIAM Journal on Optimization, 31(4), 2021, pp. 2595–2620,

https://doi.org/10.1137/21M1404363.

Biswas, A., & Hoyle, C., An approach to Bayesian optimization for design feasibility check on discontinuous black-box functions, Journal of Mechanical Design, 143(3), 2021.

Wiering, M. A., & Van Otterlo, M., Adaptation, learning, and optimization,

Reinforcement learning., 12(3), (2012). 729.

Guo, TD, Han, CY, Tang, SQ, Ding, M, Solving Combinatorial Problems with Machine Learning Methods, International Conference on Web Information Systems Engineering (WISE), 2019, pp. 111–126,

https://doi.org/10.1007/978-3-030-16194-1_9.

Jaimungal, S, Reinforcement learning and stochastic optimization, Computational Management Science, 18, 2021), pp. 531–557. https://doi.org/10.1007/s00780-021-00467-2

Nüsken, N., & Richter, L., Solving high-dimensional Hamilton–Jacobi–Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space, Partial differential equations and applications, 2(4), 2021, 48.

Cuomo, S, Di Cola, VS; Giampaolo, F; Rozza, G; Raissi, M, Piccialli, F, Scientific Machine Learning Through Physics-Info, 2022, 88, https://doi.org/10.1007/s10915-022-01939-z.

Jagtap, AD, Kawaguchi, K, Karniadakis, GE, Adaptive activation functions accelerate convergence in deep and physics-informed neural networks, Journal of Computational Physics, 404, 2019, Article 109136. https://doi.org/10.1016/j.jcp.2019.109136.


Refbacks

  • There are currently no refbacks.


JOURNAL INDEXED IN :