6 papers
Multi-Variable Conformal Prediction: Optimizing Prediction Sets without Data Splitting
Laura Lützow, Simone Garatti, Marco C. Campi +2
Conformal prediction constructs prediction sets with finite-sample coverage guarantees, but its calibration stage is structurally constrained to a scalar score function and a singl…
Formally Verifying Analog Neural Networks Under Process Variations Using Polynomial Zonotopes
Yasmine Abu-Haeyeh, Tobias Ladner, Matthias Althoff +1
Analog neural networks are gaining attention due to their efficiency in terms of power consumption and processing speed. However, since analog neural networks are implemented as ph…
To Learn or Not to Learn: A Litmus Test for Using Reinforcement Learning in Control
Victor Schulte, Michael Eichelbeck, Matthias Althoff
Reinforcement learning (RL) can be a powerful alternative to classical control methods when standard model-based control is insufficient, e.g., when deriving a suitable model is in…
Divide and Discard: Fast Tightening of Guaranteed State Bounds for Nonlinear Systems
Nico Holzinger, Matthias Althoff
We propose a simple yet effective divide-and-discard (DD) approach to guaranteed state estimation for nonlinear discrete-time systems. Our method iteratively subdivides interval en…
From Zonotopes to Proof Certificates: A Formal Pipeline for Safe Control Envelopes
Jonathan Hellwig, Lukas Schäfer, Long Qian +2
Synthesizing controllers that enforce both safety and actuator constraints is a central challenge in the design of cyber-physical systems. State-of-the-art reachability methods bas…
Approximability of the Containment Problem for Zonotopes and Ellipsotopes
Adrian Kulmburg, Lukas Schäfer, Matthias Althoff
The zonotope containment problem, i.e., whether one zonotope is contained in another, is a central problem in control theory. Applications include detecting faults and robustifying…