A scalable verification framework for neural control barrier functions uses linear bound propagation on network gradients combined with McCormick relaxations to certify safety conditions for control-affine systems.
Policy verification in stochastic dynamical systems using logarithmic neural certificates
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Scalable Verification of Neural Control Barrier Functions Using Linear Bound Propagation
A scalable verification framework for neural control barrier functions uses linear bound propagation on network gradients combined with McCormick relaxations to certify safety conditions for control-affine systems.