Intelligent systems, much like humans, have the ability to see and respond to the world around them. Using data in new ways to make more accurate predictions or enabling new services, these machines offer the hope of overcoming the limitations of our own decision-making. However, with this they bring questions about how we make decisions, the influence of bias in decision making and how experts can ensure that key values – such as fairness – are built into artificially intelligent systems. This talk will introduce the emerging theory of algorithmic fairness: how to use the tools of theoretical computer science to clarify -- and address -- the challenges experts face in ensuring that machines make objective decisions.
Cynthia Dwork, the Gordon McKay Professor of Computer Science at the John A. Paulson School of Engineering and Applied Sciences at Harvard, the Radcliffe Alumnae Professor at the Radcliffe Institute for Advanced Study, and an Affiliated Faculty Member at Harvard Law School, is renowned for placing privacy-preserving data analysis on a mathematically rigorous foundation. A cornerstone of this work is the invention of differential privacy, a strong privacy guarantee now used widely in industry and for disclosure control in the 2020 decennial census. With seminal contributions in cryptography, distributed computing, and ensuring statistical validity, her most recent focus is on fairness in classification algorithms. Dwork is a member of the US National Academy of Sciences, the US National Academy of Engineering, and the American Philosophical Society, and is a Fellow of the American Academy of Arts and Sciences and of the ACM.