Cambridge Public Health Seminar: Scaling Causal Reasoning- Beyond Prediction in Complex Real-World Systems

We are delighted to invite you to the next Cambridge Public Health Seminar, with Professor Mihaela van der Schaar on Scaling Causal Reasoning. The seminar will explore how machine learning can move beyond prediction to answer causal “what if?” questions in complex real-world settings.

Causal reasoning requires answering interventional and counterfactual questions about the mechanisms that generate data — not just predicting what comes next. This is highly relevant to public health, where many questions depend on understanding how complex systems work, how interventions may affect outcomes, and what might happen under different policy or practice choices.

In this seminar, Professor van der Schaar will discuss how causal reasoning can be scaled in machine learning, particularly in complex real-world settings where causal structures are large, only partially specified, and rarely accompanied by ground-truth supervision. She will argue that the challenge is not simply one of model capacity, but of representation and supervision.

The seminar will outline a new perspective on scaling causal reasoning — one that reframes the problem as constructing and leveraging causal simulators capable of supporting interventional and counterfactual queries at scale. 

This is joint work with Professor van der Schaar’s students Anita Kriz and Nicolas Astorga. Professor Mihaela van der Schaar is the John Humphrey Plummer Professor of Machine Learning, Artificial Intelligence and Medicine at the University of Cambridge. In addition to leading the van der Schaar Lab, she is founder and director of the Cambridge Centre for AI in Medicine.

Registration