Recent discussion in the public sphere about classification by algorithms has involved tension between competing notions of what it means for such a classification to be fair to different groups. We consider several of the key fairness conditions that lie at the heart of these debates, and discuss recent research establishing inherent trade-offs between these conditions. In the process, we find certain fundamental limits on the level of fairness that can be achieved in this family of classification problems.
11:00 à 12:00
