An approximate zero-one law via the Dialectica interpretation

Abstract: Zero-one laws state that probabilistic events of a certain type must occur with probability either $0$ or $1$, and nothing in between. We formulate a syntactic zero-one law, which enjoys good logical properties while being broadly applicable in probability theory. Then, inspired by G\"odel's Dialectica interpretation, we finitise it: The result is an approximate zero-one law which states that events with a particular finite structure occur with probability close to $0$ or $1$ up to an arbitrary degree of precision. This approximate zero-one law is equivalent - over classical logic - to the original zero-one law, but in contrast to the latter, is formulated entirely in terms of finite unions and intersections of events. Furthermore, in line with recent logical metatheorems for probability, it admits a computational interpretation, which in turn facilitates a quantitative analysis of theorems whose proof makes use of zero-one laws. Concrete applications in this spirit, over a variety of different settings, are discussed.