Skip to main content Skip to secondary navigation
Main content start

Cynthia Dwork on Measuring Our Chances: Risk Prediction in This World and its Betters

Event Details:

Thursday, January 11, 2024
6:30pm - 9:00pm PST


Stanford University Mackenzie Room, Huang Engineering Center, 475 Via Ortega Stanford, CA 94305

This event is open to:

General Public

Stanford Data Science was pleased to host our Winter Distinguished Lecture on January 11th, 2024. Our speaker is Dr. Cynthia Dwork, the 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.

Dr. Dwork's talk is titled: Measuring Our Chances: Risk Prediction in This World and its Betters.

We welcome you to join us at 6:30pm for a dinner reception and an opportunity to engage with others in the Stanford Data Science community, followed by the lecture at 7:30pm. The Reception and Check-in are located on the 2nd Floor. 


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 this student will graduate within 4 years of admission. But what do words like “chance,” “probability,” and “likelihood” actually mean for a non-repeatable activity like going to college? This is a deep and unresolved problem in the philosophy of probability. Without a compelling mathematical definition, we cannot specify what an (imagined) perfect risk prediction algorithm should produce, nor even how an existing algorithm should be evaluated.

Outcome Indistinguishability, a notion with roots in complexity theory, provides an avenue of attack. Outcome Indistinguishability (OI) frames learning not as loss minimization – the dominant paradigm in supervised machine learning -- but instead satisfaction of a collection of “indistinguishability” constraints. OI considers two alternate worlds on individual-outcome pairs: in the natural world, individual outcomes are generated by Real-Life’s true distribution; in the simulated world, individuals’ outcomes are sampled according to the predictive model. OI requires the learner to produce a predictor in which the two worlds are computationally indistinguishable (Dwork, Kim, Reingold, Rothblum, Yona, STOC 2021). The notion has provided a generous springboard, first and foremost in machine learning, and, very recently, in complexity theory.

Outcome Indistinguishability generalizes multicalibration, a concept arising in the study of algorithmic fairness (Hébert-Johnson, Kim, Reingold, Rothblum, ICML 2018). A question lingers: both (1) our qualifications, health, and skills, which form the inputs to a prediction algorithm, and (2) our chances of future success, which are the desired outputs from the risk prediction algorithm, are products of our interactions with a systematically inequitable real world. How, and when, can we hope to simulate not this world, but a better world, one for which, unfortunately, we have no data at all (Dwork, Reingold, Rothblum, FORC 2023)?

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 thirty 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.

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.

Related Topics

Explore More Events

No events at this time. Please check back later.