Compact Optimality Verification for Optimization Proxies
Not on the map. Why?
Abstract (arXiv)
Recent years have witnessed increasing interest in optimization proxies, i.e., machine learning models that approximate the input-output mapping of parametric optimization problems and return near-optimal feasible solutions. Following recent work by (Nellikkath & Chatzivasileiadis, 2021), this paper reconsiders the optimality verification problem for optimization proxies, i.e., the determination of the worst-case optimality gap over the instance distribution. The paper proposes a compact formulation for optimality verification and a gradient-based primal heuristic that brings substantial computational benefits to the original formulation. The compact formulation is also more general and applies to non-convex optimization problems. The benefits of the compact formulation are demonstrated on large-scale DC Optimal Power Flow and knapsack problems.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 40 of its 51 references that are in the map. First posted on arXiv 31 May 2024.
Builds on
40 of 51 references.
References · 40
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2013Intriguing properties of neural networkscited by 5,114
- 2021Convex optimizationcited by 2,479
- 2016End to End Learning for Self-Driving Carscited by 1,000
- 2016Neural Combinatorial Optimization with Reinforcement Learningcited by 600
- 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 588
- 2017Learning Combinatorial Optimization Algorithms over Graphscited by 557
- 2019Differentiable Convex Optimization Layerscited by 458
- 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 411
- 2016Input Convex Neural Networkscited by 407
- 2019An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problemcited by 265
- 2021Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verificationcited by 224
28 more
- 2020Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifierscited by 183
- 2021DC3: A learning method for optimization with hard constraintscited by 181
- 2018Semidefinite relaxations for certifying robustness to adversarial examplescited by 178
- 2020Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphscited by 115
- 2022General Cutting Planes for Bound-Propagation-Based Neural Network Verificationcited by 102
- 2019Predicting AC Optimal Power Flows: Combining Deep Learning and Lagrangian Dual Methodscited by 93
- 2022Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Boundcited by 92
- 2019The Power Grid Library for Benchmarking AC Optimal Power Flow Algorithmscited by 63
- 2022Self-Supervised Primal-Dual Learning for Constrained Optimizationcited by 60
- 2020Differentially Private and Fair Deep Learning: A Lagrangian Dual Approachcited by 53
- 2019DeepOPF: A Deep Neural Network Approach for Security-Constrained DC Optimal Power Flowcited by 50
- 2023End-to-End Feasible Optimization Proxies for Large-Scale Economic Dispatchcited by 35
- 2022Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxationcited by 32
- 2023RAYEN: Imposition of Hard Convex Constraints on Neural Networkscited by 30
- 2021Learning Optimization Proxies for Large-Scale Security-Constrained Economic Dispatchcited by 29
- 2020Learning Optimal Power Flow: Worst-Case Guarantees for Neural Networkscited by 28
- 2020RNA Secondary Structure Prediction By Learning Unrolled Algorithmscited by 24
- 2021Physics-Informed Neural Networks for Minimising Worst-Case Violations in DC Optimal Power Flowcited by 23
- 2022Learning to Solve Optimization Problems with Hard Linear Constraintscited by 23
- 2022Alternating Differentiation for Optimization Layerscited by 22
- 2021Learning Hard Optimization Problems: A Data Generation Perspectivecited by 21
- 2021Fast Approximations for Job Shop Scheduling: A Lagrangian Dual Deep Learning Methodcited by 20
- 2022The Curse of Unrolling: Rate of Differentiating Through Optimizationcited by 15
- 2023Compact Optimization Learning for AC Optimal Power Flowcited by 11
- 2023Dual Conic Proxies for AC Optimal Power Flowcited by 11
- 2021DeepSplit: Scalable Verification of Deep Neural Networks via Operator Splittingcited by 8
- 2024Bound Tightening using Rolling-Horizon Decomposition for Neural Network Verificationcited by 6
- 2023Real-Time Risk Analysis with Optimization Proxiescited by 5
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.