Downward causation is the controversial idea that 'higher'levels of organization can causally
influence behaviour at 'lower'levels of organization. Here I propose that we can gain traction …

Shannon information theory provides various measures of so-called syntactic information,
which reflect the amount of statistical correlation between systems. By contrast, the concept …

The formulation of the Partial Information Decomposition (PID) framework by Williams and
Beer in 2010 attracted a significant amount of attention to the problem of defining redundant …

Abstract Machine learning (ML) models can underperform on certain population groups due
to choices made during model development and bias inherent in the data. We categorize …

What are the distinct ways in which a set of predictor variables can provide information about
a target variable? When does a variable provide unique information, when do variables …

We consider the “partial information decomposition”(PID) problem, which aims to
decompose the information that a set of source random variables provide about a target …

Based on a recently reported operative definition of semantic information, due to Kolchinsky
and Wolpert (2018), here we present a research program based on the intersection between …

According to the subjective Bayesian interpretation of quantum mechanics (QBism), the
instruments used to measure quantum systems are to be regarded as an extension of the …

We introduce two new classes of measures of information for statistical experiments which
generalise and subsume φ-divergences, integral probability metrics, N-distances (MMD) …

The entropy of a pair of random variables is commonly depicted using a Venn diagram. This
representation is potentially misleading, however, since the multivariate mutual information …