Strong mixed-integer programming formulations for trained neural networks

2020/02/13 by Ross Anderson, Joey Huchette, Will Ma +2 · 16 citations
Computer Science · #Adversarial Robustness in Machine Learning #Machine Learning and Algorithms #Advanced Neural Network Applications

paper · doi:10.1007/s10107-020-01474-5

Citations

• Gradient-based learning applied to document recognition
• Deep Reinforcement Learning: A Brief Survey

Cited by

• Order-2 Tightness of Block-Sparse SOS Relaxations for One-Layer ReLU Network Verification with a Matching Input-Sharing Graph
• IoUCert: Robustness Verification for Anchor-based Object Detectors
• Random Parameter Noise Does Not Make Exact ReLU Verification Easy
• Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification
• Sparse Neural Approximations for Bilevel Adversarial Problems in Power Grids
• BEAVER: An Efficient Deterministic LLM Verifier
• Faster Verified Explanations for Neural Networks
• Verification of Sequential Convex Programming for Parametric Non-convex Optimization
• An Outer-approximation Guided Optimization Approach for Constrained Neural Network Inverse Problems
• Neural Two-Stage Stochastic Volt-VAR Optimization for Three-Phase Unbalanced Distribution Systems with Network Reconfiguration
• PySCIPOpt-ML: Embedding Trained Machine Learning Models into Mixed-Integer Programs
• PolyKAN: A Polyhedral Analysis Framework for Provable and Approximately Optimal KAN Compression
• Stochastic Sample Approximations of (Local) Moduli of Continuity
• Probabilistic Robustness Analysis in High Dimensional Space: Application to Semantic Segmentation Network
• Superstructure Optimization with Embedded Neural Networks for Sustainable Aviation Fuel Production
• Optimal Data Reduction under Information-Theoretic Criteria
• A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks