155 citations · 364 across the 31 of their papers we have counts for
36 papers
Why AI Safety Requires Uncertainty, Incomplete Preferences, and Non-Archimedean Utilities
Alessio Benavoli, Alessandro Facchini, Marco Zaffalon
How can we ensure that AI systems are aligned with human values and remain safe? We can study this problem through the frameworks of the AI assistance and the AI shutdown games. Th…
The AI off-switch problem as a signalling game: bounded rationality and incomparability
Alessio Benavoli, Alessandro Facchini, Marco Zaffalon
The off-switch problem is a critical challenge in AI control: if an AI system resists being switched off, it poses a significant risk. In this paper, we model the off-switch proble…
dynoGP: Deep Gaussian Processes for dynamic system identification
Alessio Benavoli, Dario Piga, Marco Forgione +1
In this work, we present a novel approach to system identification for dynamical systems, based on a specific class of Deep Gaussian Processes (Deep GPs). These models are construc…
A tutorial on learning from preferences and choices with Gaussian Processes
Alessio Benavoli, Dario Azzimonti
Preference modelling lies at the intersection of economics, decision theory, machine learning and statistics. By understanding individuals' preferences and how they make choices, w…
Connecting classical finite exchangeability to quantum theory
Alessio Benavoli, Alessandro Facchini, Marco Zaffalon
Exchangeability is a fundamental concept in probability theory and statistics. It allows to model situations where the order of observations does not matter. The classical de Finet…
Learning Choice Functions with Gaussian Processes
Alessio Benavoli, Dario Azzimonti, Dario Piga
In consumer theory, ranking available objects by means of preference relations yields the most common description of individual choices. However, preference-based models assume tha…