"Using regret bounds from Online Convex Optimization, we obtain rigorous guarantees on the asymptotic power of the tests for a wide range of alternative hypotheses. Our results allow for bounded and unbounded data distributions, assuming that a sub-ψ tail bound is satisfied."
“... this article provides anchorage to scholarly audiences when scrutinizing the extent to which privacy and security measures qualify as ‘appropriate’ in the context of liability claims and actions
“Our results have implications for insurance contract design, particularly in the realm of long-term contracting.” LIRE
“This paper provides a comprehensive analysis of the recent EU AI Act, the regulatory framework surrounding Artificial Intelligence (AI), focusing on foundation models, open-source exemptions, remote