Robustness analysis of continuous-depth models with Lagrangian techniques

DOI10.1007/978-3-031-22337-2_30zbMath1528.68231arXiv2308.12192MaRDI QIDQ6113998

Radu Grosu, Sophie A. Neubauer

Publication date: 10 August 2023

Published in: Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2308.12192

zbMATH Keywords

verificationmachine learningcontinuous-depth models

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Specification and verification (program logics, model checking, etc.) (68Q60)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Lipschitz global optimization methods in control problems
• Validated solutions of initial value problems for ordinary differential equations
• Reachability analysis of nonlinear systems using hybridization and dynamics scaling
• CAPD::DynSys: a flexible C++ toolbox for rigorous numerical analysis of dynamical systems
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Lagrangian reachabililty
• Improved geometric path enumeration for verifying ReLU neural networks
• Stochastic global optimization.
• Stochastic reachability of a target tube: theory and computation
• Measurability and safety verification for stochastic hybrid systems
• ProbReach
• Bounds on Real Eigenvalues and Singular Values of Interval Matrices
• Bounded Verification with On-the-Fly Discrepancy Computation
• Systematic Simulation Using Sensitivity Analysis
• Bounds on Eigenvalues of Interval Matrices
• Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks
• TIRA
• Complete search in continuous global optimization and constraint satisfaction
• Computational error bounds for multiple or nearly multiple eigenvalues

This page was built for publication: Robustness analysis of continuous-depth models with Lagrangian techniques