Differentiable Integer Linear Programming is not Differentiable & it's not a mere technical problem
Not on the map. Why?
Abstract (arXiv)
We show how the differentiability method employed in the paper ``Differentiable Integer Linear Programming'', Geng, et al., 2025 as shown in its theorem 5 is incorrect. Moreover, there already exists some downstream work that inherits the same error. The underlying reason comes from that, though being continuous in expectation, the surrogate loss is discontinuous in almost every realization of the randomness, for the stochastic gradient descent.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 10 of its 20 references that are in the map. First posted on arXiv 25 Jan 2026.
Builds on
10 of 20 references.
References · 10
- 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
- 2025Apollo-MILP: An Alternating Prediction-Correction Neural Solving Framework for Mixed-Integer Linear Programmingcited by 16
- 2023Differentiable Clustering with Perturbed Spanning Forestscited by 14
- 2025CoCo-MILP: Inter-Variable Contrastive and Intra-Constraint Competitive MILP Solution Predictioncited by 4
- 2025RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domainscited by 3
- 2024When Simple is Near Optimal in Security Gamescited by 2
- 2025Constraint Matters: Multi-Modal Representation for Reducing Mixed-Integer Linear programmingcited by 2
- 2025DEFT: Differentiable Automatic Test Pattern Generationcited by 2
- 2025Hephaestus: Mixture Generative Modeling with Energy Guidance for Large-scale QoS Degradationcited by 1
- 2025Learning-Based Hierarchical Approach for Fast Mixed-Integer Optimizationcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.