Bayesian Fairness

Christos Dimitrakakis, Chalmers University / University of Oslo

When:
Monday, June 10, 2019
Event Start Time: 11:00 am
Event End Time: 12:30 pm (includes lunch following lecture)
Where:
Hariri Institute for Computing, Seminar Room, MCS 180

Abstract: Bayesian fairness is an overarching concept of fairness that explicitly takes into account the subjective uncertainty of the decision maker. This allows us to be as fair as possible, for most standard definitions of fairness, even under high uncertainty. It also enables decision-making policies that explicitly take into account informational feedback effects, leading to an intertemporal notion of fairness.

Bio: My research in artificial intelligence and machine learning includes reinforcement learning, preference elicitation, privacy, fairness, experiment design, safety, recommendation systems, job matching, crowdsourcing, and social computing more generally. More recently, I have been interested in the computational, societal and statistical problems that arise when humans interact with artificially intelligent systems. I obtained my PhD in 2006 from EPFL, and I am currently an associate professor at the University of Oslo and a senior researcher at Chalmers University.