Our weekly SRI Seminar Series welcomes Cynthia Dwork, Gordon McKay Professor of Computer Science at the Harvard University John A. Paulson School of Engineering and Applied Sciences and affiliated faculty at Harvard Law School. She uses theoretical computer science to place societal problems on a firm mathematical foundation.
In this talk, Dwork will discuss what words like “chance,” “probability,” and “likelihood” mean for a non-repeatable activity and survey the confluence of fairness, complexity, and prediction in the work of algorithmic fairness.
Dwork’s recent awards and honours include the 2020 ACM SIGACT and IEEE TCMF Knuth Prize, the 2020 IEEE Hamming Medal, and the 2017 Gödel Prize. This session will be moderated by David Lie.
Talk title:
“Prediction, fairness, and... complexity theory?”
Abstract:
Prediction algorithms score individuals, assigning a number between zero and one that is often interpreted as an individual probability: a 0.7 “chance” that this child is in danger in the home; an 80% “probability” that this woman will succeed if hired; a 1/3 “likelihood” that they will graduate within 4 years of admission. But what do words like “chance,” “probability,” and “likelihood” mean for a non-repeatable activity like going to college? Absent an answer to this question, how can we even specify the goal, let alone evaluate the quality of, a prediction algorithm? Undaunted, machine-learned algorithms churn these numbers out in droves, sometimes with life-altering consequences.
An explosion of research in the theory of algorithmic fairness deploys insights from complexity theory to yield some tantalizing answers to these questions, together with a supporting algorithmic framework.
This talk will survey the confluence of fairness, complexity, and prediction, tracing the history of key concepts and revealing some surprising contributions of fairness concepts to deep learning and complexity, even when fairness is not a concern.
About Cynthia Dwork
Cynthia Dwork, Gordon McKay Professor of Computer Science at the John A. Paulson School of Engineering and Applied Sciences at Harvard, and affiliated faculty at the Harvard Law School and the Department of Statistics, is renowned for placing privacy-preserving data analysis on a mathematically rigorous foundation. A cornerstone of this work is differential privacy, a strong privacy guarantee permitting sophisticated data analysis. Differential privacy is widely deployed in industry, including in every Apple device, and is the backbone of the Disclosure Avoidance System for the 2020 US Decennial Census.
Dwork joined Harvard after more than 30 years in industrial research at IBM and Microsoft. Some of her earliest work established the pillars on which every fault-tolerant distributed system has been built for decades.
Her innovations modernized cryptography to cope with the ungoverned interactions of the internet through the development of non-malleable cryptography; provided a proof-of-concept for the post-quantum era with the first lattice-based public-key cryptosystem, which also was the first to enjoy worst-case/average-case equivalence; fought email spam and formed the basis of crypto-currencies through proofs of work; and gave the first general approach to ensuring statistical validity in exploratory data analysis, via a connection to differential privacy. In 2012 she launched the theoretical investigation of algorithmic fairness, a topic experiencing explosive growth and the driving force behind the multidisciplinary Hire Aspirations Institute devoted to fairness in hiring platforms.
Dwork is a member of the US National Academy of Sciences, the US National Academy of Engineering, and the American Philosophical Society, and a fellow of the American Academy of Arts and Sciences and of the ACM. Her awards include the Gödel Prize, the ACM-IEEE Knuth Prize, the ACM Paris Kanellakis Theory and Practice Award, the RSA Mathematics Award, the IEEE Hamming Medal, and test-of-time recognition in four fields.
About the SRI Seminar Series
The SRI Seminar Series brings together the Schwartz Reisman community and beyond for a robust exchange of ideas that advance scholarship at the intersection of technology and society. Seminars are led by a leading or emerging scholar and feature extensive discussion.
Each week, a featured speaker will present for 45 minutes, followed by an open discussion. Registered attendees will be emailed a Zoom link before the event begins. The event will be recorded and posted online.
Cynthia Dwork