Vivek Farias, Professor of Operations Management, MIT Sloan

Abstract

Fair Exploration via Axiomatic Bargaining

Exploration is often necessary in online learning to maximize long-term reward, but it comes at the cost of short-term ‘regret’. We study how this cost of exploration is shared across multiple groups. Leveraging the theory of axiomatic bargaining we observe that regret optimal learning results in strikingly unfair outcomes. More constructively, we derive policies that are optimally fair and simultaneously enjoy a small ‘price of fairness’. We illustrate the relative merits of our algorithmic framework with a case study on contextual bandits for warfarin dosing where we are concerned with the cost of exploration across multiple races and age groups. 

Bio

Vivek Farias is the Patrick J. McGovern (1959) Professor at the MIT Sloan School, affiliated with the Operations Management group and the ORC. His research is focused on optimization and inference in large-scale stochastic systems.