Heilbronn Colloquium van der Schaar

13 Mar 2018, by franblake in Events

15 May 2018

University of Bristol

We are delighted to welcome Michaela van der Schaar, Oxford, to the University of Bristol for a Heilbronn Colloquium.

Mihaela van der Schaar is the Man Professor of Quantitative Finance in Oxford.  Her research interests are in machine learning, data science and decisions for a better planet. In particular, she is interested in developing machine learning and decision theory for finance, medicine and personalized education.  She is a leading expert in these areas and highly distinguished for her contributions to them.  She is Faculty Fellow at the Alan Turing Institute.  Prior to moving to Oxford in 2016, Mihaela was Chancellor’s Professor of Electrical and Computer Engineering at UCLA.

The colloquium will take place in SM1 in the Main Maths Building at 16.00 on Tuesday 15th May. It will be followed by a wine reception in the Common Room. To help us plan space and catering, please complete the short registration form if you are planning to come.

Causal Inference for Treatment Effects: A Theory and Associated Learning Algorithms

Abstract: We investigate the problem of estimating the causal effect of a treatment on individual subjects from observational data; this is a central problem in various application domains, including healthcare, social sciences, and online advertising. We first develop a theoretical foundation of causal inference for individualized treatment effects based on information theory. Next, we use this theory, to construct an information-optimal Bayesian causal inference algorithm.  This algorithm embeds the potential outcomes in a vector-valued reproducing kernel Hilbert space and uses a multi-task Gaussian process prior over that space to infer the individualized causal effects. We show that our algorithm significantly outperforms the state-of-the-art causal inference algorithms. The talk will conclude with a discussion of the impact of this work on precision medicine and clinical trials.