Modern AI systems are no longer just engineering artefacts: they are decision-makers operating under uncertainty, constraints, and societal needs. This summer school concerns the intersection of decision theory and the theory of AI and it aims to train researchers who can reason rigorously about why AI systems behave as they do, when their conclusions are valid, and how they should interact with humans and institutions.

While AI methods advance rapidly, theoretical foundations connecting learning, inference, explanation, and responsibility are often fragmented across fields. Decision theory provides a unifying language—utility, uncertainty, optimality, and risk—that ties together statistical rigor, algorithmic design, and privacy constraints.

Topics: privacy, explainable AI, anytime valid hypothesis testing, algorithmic statistics, and reinforcement learning.

Goal: at the summer school on DTAIL you will

• Be trained as part of a new generation of researchers fluent in theoretical rigor.

• Build a strong network in mathematical machine learning.