collaborators

8 papers

cs.LG2025

On the Probabilistic Learnability of Compact Neural Network Preimage Bounds

Luca Marzari, Manuele Bicego, Ferdinando Cicalese +1

Although recent provable methods have been developed to compute preimage bounds for neural networks, their scalability is fundamentally limited by the #P-hardness of the problem. I…

cs.LG2025

Probabilistically Tightened Linear Relaxation-based Perturbation Analysis for Neural Network Verification

Luca Marzari, Ferdinando Cicalese, Alessandro Farinelli

We present robabilistically ightened near elaxation-based erturbation nalysis (), a nove…

cs.AI2025

Advancing Neural Network Verification through Hierarchical Safety Abstract Interpretation

Luca Marzari, Isabella Mastroeni, Alessandro Farinelli

Traditional methods for formal verification (FV) of deep neural networks (DNNs) are constrained by a binary encoding of safety properties, where a model is classified as either saf…

cs.AI2025

Learning Symbolic Persistent Macro-Actions for POMDP Solving Over Time

Celeste Veronese, Daniele Meli, Alessandro Farinelli

This paper proposes an integration of temporal logical reasoning and Partially Observable Markov Decision Processes (POMDPs) to achieve interpretable decision-making under uncertai…

cs.AI2025

Designing Control Barrier Function via Probabilistic Enumeration for Safe Reinforcement Learning Navigation

Luca Marzari, Francesco Trotti, Enrico Marchesini +1

Achieving safe autonomous navigation systems is critical for deploying robots in dynamic and uncertain real-world environments. In this paper, we propose a hierarchical control fra…

cs.RO2025

Depth-Constrained ASV Navigation with Deep RL and Limited Sensing

Amirhossein Zhalehmehrabi, Daniele Meli, Francesco Dal Santo +2

Autonomous Surface Vehicles (ASVs) play a crucial role in maritime operations, yet their navigation in shallow-water environments remains challenging due to dynamic disturbances an…