Efficient neural network analysis with sum-of-infeasibilities

DOI10.1007/978-3-030-99524-9_8zbMATH Open1547.68461MaRDI QIDQ6535564

Clark Barrett, Aleksandar Zeljić, Haoze Wu, Guy Katz

Publication date: 23 January 2024

zbMATH Keywords

convex optimizationneural networksstochastic local searchsum of infeasibilities

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Specification and verification (program logics, model checking, etc.) (68Q60)

Cites Work

• Unnamed Item
• Unnamed Item
• An introduction to MCMC for machine learning
• Safety verification of deep neural networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Verification of deep convolutional neural networks using ImageStars
• Improved geometric path enumeration for verifying ReLU neural networks
• The generalized simplex method for minimizing a linear form under linear inequality restraints
• Handbook of Markov Chain Monte Carlo
• Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks
• Experiments in mixed-integer linear programming
• Strong mixed-integer programming formulations for trained neural networks

Related Items (3)

Towards formal XAI: formally approximate minimal explanations of neural networks ⋮ Verifying generalization in deep learning ⋮ Verifying the generalization of deep learning to out-of-distribution domains

This page was built for publication: Efficient neural network analysis with sum-of-infeasibilities