Solving the linear programming-based neural network verification problem through Alternating Direction Method of Multipliers (ADMM).
-
Updated
Jan 20, 2024 - Python
Solving the linear programming-based neural network verification problem through Alternating Direction Method of Multipliers (ADMM).
Finite differences, von Neumann stability and Lie vs Strang operator splitting, verified on Fisher-KPP; Gray-Scott patterns
PyTorch implementation of a two-block cascaded equilibrium iteration with convergence diagnostics and selected VRI results.
To associate your repository with the operator-splitting topic, visit your repo's landing page and select "manage topics."