Axiomatization of Interventional Probability Distributions

Add to your list(s) Download to your calendar using vCal

• Kayvan Sadeghi (University College London)
• Wednesday 13 November 2024, 15:00-16:00
• Seminar Room 2, Newton Institute.

If you have a question about this talk, please contact nobody.

SSD - Stochastic systems for anomalous diffusion

Causal intervention is an essential tool in causal inference. It is axiomatized under the rules of do-calculus in the case of structure causal models. We provide simple axiomatizations for families of probability distributions to be different types of interventional distributions. Our axiomatizations neatly lead to a simple and clear theory of causality that has several advantages: it does not need to make use of any modeling assumptions such as those imposed by structural causal models; it only relies on interventions on single variables; it includes most cases with latent variables and causal cycles; and more importantly, it does not assume the existence of an underlying true causal graph—in fact, a  causal graph is a by-product of our theory. We show that, under our axiomatizations, the intervened distributions are Markovian to the defined intervened causal graphs, and an observed joint probability distribution is Markovian to the obtained causal graph; these results are consistent with the case of structural causal models, and as a result, the existing theory of causal inference applies.  We also show that a large class of natural structural causal models satisfy the axioms presented here, and in other cases, the causal graphs generated by an interventional family of distributions act more naturally than those associated to structural causal models.

This talk is part of the Isaac Newton Institute Seminar Series series.

This talk is included in these lists:

• All CMS events
• Featured lists
• INI info aggregator
• Isaac Newton Institute Seminar Series
• School of Physical Sciences
• Seminar Room 2, Newton Institute
• bld31

Note that ex-directory lists are not shown.