Abstract

Co-authors: Rafael Chaves (University of Freiburg), Lukas Luft (University of Freiburg)

The fields of quantum non-locality in physics, and causal discovery in machine learning, both face the problem of deciding whether observed data is compatible with a presumed causal relationship between the variables (for example a local hidden variable model). Traditionally, Bell inequalities have been used to describe the restrictions imposed by causal structures on marginal distributions. However, some structures give rise to non-convex constraints on the accessible data, and it has recently been noted that linear inequalities on the observable entropies capture these situations more naturally. In this talk, I will introduce the machine learning background, advertise the program of investigating entropic marginals, and present some recent results.