Thursday, June 5th 2-3pm  |  LTB @ CS Dept

Abstract: In this talk, I will give an overview of the role of causality in ethical machine learning, and in particular in fair and explainable ML. Specifically, I will first describe how causal reasoning can be used to study fairness and explainability problems in algorithmic decision making, and highlight the main limitations we face when trying to address these problems in practice. I will then introduce the audience to causal generative models, a novel class of deep generative models that not only accurately fit observational data, but can also provide accurate estimates for interventional and counterfactual queries. I will focus on the advances and open challenges of causal generative models towards a practical approach for “causethical ML.”
Speaker Bio: Prof. Isabel Valera is a Full Professor at Saarland University and Adjunct Faculty at the Max Planck Institute for Software Systems. She is a fellow of ELLIS and part of its Robust Machine Learning Program. Her research focuses on ethical machine learning, causality, and probabilistic modelling. She has previously held fellowships from the Humboldt Foundation and the Max Planck Society.
The talk is open to all. Sign up below if you wish to stay for coffee and cake after the talk and a chance to chat with the speaker: 
✨ Sign up: https://forms.office.com/e/ZuWBv6zLkH