Joshua Loftus


Counterfactual fairness

Statistics Seminar

10th June 2022, 2:00 pm – 3:00 pm
Fry Building, 2.41

I will discuss a line of recent work using causal models to understand algorithmic fairness. Rather than attempting to make minimal assumptions and provide robust inferences, this approach uses strong assumptions for the sake of interpretability, transparency, and falsifiability. Although the application focus is on fairness, causal models can be applied in similar ways toward achieving other values or objectives in responsible machine learning or data-driven decisions more broadly.


Comments are closed.