Sparse polynomial optimisation for neural network verification

DOI10.1016/j.automatica.2023.111233arXiv2202.02241OpenAlexW4386006943MaRDI QIDQ6073032

Antonis Papachristodoulou, Matthew C. Newton

Publication date: 15 September 2023

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2202.02241

zbMATH Keywords

neural networkssemi-algebraic setssparse polynomial optimisation

Mathematics Subject Classification ID

Mathematical programming (90Cxx) Computer science (68-XX) Real algebraic and real-analytic geometry (14Pxx)

Related Items (1)

A Correlatively Sparse Lagrange Multiplier Expression Relaxation for Polynomial Optimization

Cites Work

• Unnamed Item
• A direct proof for the matrix decomposition of chordal-structured positive semidefinite matrices
• Positive semidefinite matrices with a given sparsity pattern
• Safety verification of deep neural networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• A Nullstellensatz and a Positivstellensatz in semialgebraic geometry
• Ensemble Machine Learning
• Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming
• Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks
• Chordal-TSSOS: A Moment-SOS Hierarchy That Exploits Term Sparsity with Chordal Extension

This page was built for publication: Sparse polynomial optimisation for neural network verification