OCLGNov 12, 2025

Scalable Mixed-Integer Optimization with Neural Constraints via Dual Decomposition

arXiv:2511.09186v11 citationsh-index: 4
Originality Incremental advance
AI Analysis

This addresses scalability issues in optimization for researchers and practitioners in operations research and machine learning, offering a modular and adaptable solution, though it is incremental as it builds on existing dual-decomposition methods.

The paper tackles the problem of embedding deep neural networks into mixed-integer programs for decision-making with learned constraints, which often becomes intractable due to large linearizations, and introduces a dual-decomposition framework that splits the problem into MIP and NN subproblems, resulting in a 120x speedup on the largest test case compared to an exact Big-M formulation.

Embedding deep neural networks (NNs) into mixed-integer programs (MIPs) is attractive for decision making with learned constraints, yet state-of-the-art monolithic linearisations blow up in size and quickly become intractable. In this paper, we introduce a novel dual-decomposition framework that relaxes the single coupling equality u=x with an augmented Lagrange multiplier and splits the problem into a vanilla MIP and a constrained NN block. Each part is tackled by the solver that suits it best-branch and cut for the MIP subproblem, first-order optimisation for the NN subproblem-so the model remains modular, the number of integer variables never grows with network depth, and the per-iteration cost scales only linearly with the NN size. On the public \textsc{SurrogateLIB} benchmark, our method proves \textbf{scalable}, \textbf{modular}, and \textbf{adaptable}: it runs \(120\times\) faster than an exact Big-M formulation on the largest test case; the NN sub-solver can be swapped from a log-barrier interior step to a projected-gradient routine with no code changes and identical objective value; and swapping the MLP for an LSTM backbone still completes the full optimisation in 47s without any bespoke adaptation.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes