mlsanityData to 14 Oct 2026

Learning to Optimize for Mixed-Integer Non-linear Programming with Feasibility Guarantees

arXiv 2410.11061 ↗First posted 14 Oct 2024cs.LG math.OCcited by 8

Not on the map. Why?

Abstract (arXiv)

Mixed-integer nonlinear programs (MINLPs) arise in domains such as energy systems, process engineering, and transportation, and are notoriously difficult to solve at scale due to the interplay of discrete decisions and nonlinear constraints. In many practical settings, these problems appear in parametric form, where objectives and constraints depend on instance-specific parameters, creating the need for fast and reliable solutions across related instances. While learning-to-optimize (L2O) methods have shown strong performance in continuous optimization, extending them to MINLPs requires enforcing both feasibility and integrality within a data-driven framework. We propose an L2O approach tailored to parametric MINLPs that generates instance-specific solutions using integer correction layers to enforce integrality and a gradient-based projection to ensure feasibility of the inequality constraints. Theoretically, we provide asymptotic and non-asymptotic convergence guarantees of the projection step. Empirically, the framework scales to MINLPs with tens of thousands of variables and produces feasible high-quality solutions within milliseconds, often outperforming traditional solvers and heuristic baselines in repeated-solve settings.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 68 of its 124 references that are in the map. First posted on arXiv 14 Oct 2024.

Builds on

68 of 124 references.

References · 68

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  3. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  4. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  5. 2015Pointer Networkscited by 895
  6. 2018Attention, Learn to Solve Routing Problems!cited by 656
  7. 2018Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizoncited by 623
  8. 2016Neural Combinatorial Optimization with Reinforcement Learningcited by 608
  9. 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 599
  10. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  11. 2017Learning Combinatorial Optimization Algorithms over Graphscited by 561
  12. 2019Differentiable Convex Optimization Layerscited by 465
38 more
  1. 2018Lipschitz regularity of deep neural networks: analysis and efficient estimationcited by 415
  2. 2017Smart "Predict, then Optimize"cited by 339
  3. 2019Exact Combinatorial Optimization with Graph Convolutional Neural Networkscited by 318
  4. 2018Regularisation of Neural Networks by Enforcing Lipschitz Continuitycited by 314
  5. 2019Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networkscited by 293
  6. 2017How to Escape Saddle Points Efficientlycited by 285
  7. 2019An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problemcited by 269
  8. 2021Combinatorial optimization and reasoning with graph neural networkscited by 268
  9. 2018Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimizationcited by 227
  10. 2019Differentiation of Blackbox Combinatorial Solverscited by 226
  11. 2021Learning to Optimize: A Primer and A Benchmarkcited by 208
  12. 2021Efficient and Modular Implicit Differentiationcited by 203
  13. 2021DC3: A learning method for optimization with hard constraintscited by 184
  14. 2020Solving Mixed Integer Programs Using Neural Networkscited by 182
  15. 2021End-to-End Constrained Optimization Learning: A Surveycited by 157
  16. 2021NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving the Traveling Salesman Problemcited by 103
  17. 2015Constrained Convolutional Neural Networks for Weakly Supervised Segmentationcited by 100
  18. 2019MIPaaL: Mixed Integer Program as a Layercited by 94
  19. 2019Predicting AC Optimal Power Flows: Combining Deep Learning and Lagrangian Dual Methodscited by 94
  20. 2020Learning Combinatorial Optimization on Graphs: A Survey with Applications to Networkingcited by 70
  21. 2020Parameterizing Branch-and-Bound Search Trees to Learn Branching Policiescited by 63
  22. 2022Self-Supervised Primal-Dual Learning for Constrained Optimizationcited by 61
  23. 2017Constrained Deep Weak Supervision for Histopathology Image Segmentationcited by 51
  24. 2019DeepOPF: A Deep Neural Network Approach for Security-Constrained DC Optimal Power Flowcited by 50
  25. 2022MIP-GNN: A Data-Driven Framework for Guiding Combinatorial Solverscited by 49
  26. 2021Learning to Schedule Heuristics in Branch-and-Boundcited by 46
  27. 2023Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Modelcited by 45
  28. 2022A Survey for Solving Mixed Integer Programming via Machine Learningcited by 44
  29. 2017Imposing Hard Constraints on Deep Networks: Promises and Limitationscited by 43
  30. 2021Learning a Large Neighborhood Search Algorithm for Mixed Integer Programscited by 43
  31. 2023A GNN-Guided Predict-and-Search Framework for Mixed-Integer Linear Programmingcited by 41
  32. 2022On Representing Linear Programs by Graph Neural Networkscited by 39
  33. 2019Online Mixed-Integer Optimization in Millisecondscited by 38
  34. 2023Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learningcited by 37
  35. 2023End-to-End Feasible Optimization Proxies for Large-Scale Economic Dispatchcited by 35
  36. 2019Constrained Deep Networks: Lagrangian Optimization via Log-Barrier Extensionscited by 30
  37. 2023RAYEN: Imposition of Hard Convex Constraints on Neural Networkscited by 30
  38. 2022End-to-End Learning to Warm-Start for Real-Time Quadratic Optimizationcited by 26

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 6.

8 papers.

  1. 2025Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfactioncited by 6
  2. 2026AutoOR: Scalably Post-training LLMs to Autoformulate Operations Research Problemscited by 1
  3. 2026Solving Max-Cut to Global Optimality via Feasibility-Preserving Graph Neural Networkscited by 1
  4. 2025Accelerating Fleet Upgrade Decisions with Machine-Learning Enhanced Optimizationcited by 0
  5. 2026partialCBDs: Differentiable Causal Block Diagramscited by 0
  6. 2026Towards Solving Polynomial-Objective Integer Programming with Hypergraph Neural Networkscited by 0
  7. 2026Constrained Graph Diffusion for Mixed Integer Optimizationcited by 0
  8. 2026Mixed-Integer Nonlinear Differentiable Predictive Control for Underground Pumped Hydro Energy Storage Systemscited by 0