collaborators

5 papers

cs.LG2026

Certified Neural Approximations of Nonlinear Dynamics

Frederik Baymler Mathiesen, Nikolaus Vertovec, Francesco Fabiano +2

Neural networks hold great potential to act as approximate models of nonlinear dynamical systems, with the resulting neural approximations enabling verification and control of such…

cs.LG2026

Scalable Verification of Neural Control Barrier Functions Using Linear Bound Propagation

Nikolaus Vertovec, Frederik Baymler Mathiesen, Thom Badings +2

Control barrier functions (CBFs) are a popular tool for safety certification of nonlinear dynamical control systems. Recently, CBFs represented as neural networks have shown great…

math.OC2025

Finite sample learning of moving targets

Nikolaus Vertovec, Kostas Margellos, Maria Prandini

We consider a moving target that we seek to learn from samples. Our results extend randomized techniques developed in control and optimization for a constant target to the case whe…

cs.LG2025

SPoRt -- Safe Policy Ratio: Certified Training and Deployment of Task Policies in Model-Free RL

Jacques Cloete, Nikolaus Vertovec, Alessandro Abate

To apply reinforcement learning to safety-critical applications, we ought to provide safety guarantees during both policy training and deployment. In this work, we present theoreti…

eess.SY2025

Certified Approximate Reachability (CARe): Formal Error Bounds on Deep Learning of Reachable Sets

Prashant Solanki, Nikolaus Vertovec, Yannik Schnitzer +3

Recent approaches to leveraging deep learning for computing reachable sets of continuous-time dynamical systems have gained popularity over traditional level-set methods, as they o…