Abstract: Causal discovery aims at inferring cause–effect relationships between variables from observational data. Recently, there has been notable progress in Bayesian inference of causal graphs, which holds the promise of fully quantifying the uncertainty over competitive causal hypotheses. In this talk, I will highlight the power of the Bayesian paradigm for modeling and inference when the models of interest are only partially identifiable from data. I will argue that the challenge mainly stems from the computational complexity, and give an example of my team’s ongoing research. On the other hand, I will also critically examine the assumptions currently needed for statistically and computationally efficient Bayesian inference, including the assumption of causal sufficiency, stating that all common causes of the observed variables are observed as well.

Speaker:  Mikko Koivisto is a Professor of Computer Science at the University of Helsinki, where he also obtained his PhD in 2004. With interests generally in algorithms and artificial intelligence, his research has focused on exact and approximate algorithms for weighted counting, often inspired by applications in Bayesian machine learning.

Affiliation: University of Helsinki

Place of Seminar:  Kumpula Exactum CK111 (in person) & zoom ( Meeting ID: 640 5738 7231 ; Passcode: 825217)