With the range and sensitivity of algorithmic decisions expanding at a break-neck speed, it is imperative that we aggressively investigate fairness and bias in decision-making programs. First, we show that a number of recently proposed formal definitions of fairness can be encoded as probabilistic program properties. Second, with the goal of enabling rigorous reasoning about fairness, we design a novel technique for verifying probabilistic properties that admits a wide class of decision-making programs. Third, we present FairSquare, the first verification tool for automatically certifying that a program meets a given fairness property. We evaluate FairSquare on a range of decision-making programs. Our evaluation demonstrates FairSquare’s ability to verify fairness for a range of different programs, which we show are out-of-reach for state-of-the-art program analysis techniques.
Thu 26 Oct Times are displayed in time zone: Tijuana, Baja California change
13:30 - 13:52 Talk | Seam: Provably Safe Local Edits on Graphs OOPSLA Manolis PapadakisStanford University, USA, Gilbert Louis BernsteinStanford University, USA, Rahul SharmaMicrosoft Research, Alex AikenStanford University, Pat HanrahanStanford University, USA DOI | ||
13:52 - 14:15 Talk | TiML: A Functional Language for Practical Complexity Analysis with Invariants OOPSLA Peng WangMassachusetts Institute of Technology, USA, Di WangPeking University, China, Adam ChlipalaMassachusetts Institute of Technology, USA DOI | ||
14:15 - 14:37 Talk | FairSquare: Probabilistic Verification of Program Fairness OOPSLA Aws AlbarghouthiUniversity of Wisconsin-Madison, Loris D'AntoniUniversity of Wisconsin–Madison, Samuel DrewsUniversity of Wisconsin-Madison, Aditya Nori DOI | ||
14:37 - 15:00 Talk | Reasoning on Divergent Computations with Coaxioms OOPSLA DOI |