Date & Time:
May 3, 2022 3:30 pm – 4:30 pm
Kent 107, 1020-24 East 58th St., Chicago, IL, 60637
05/03/2022 03:30 PM 05/03/2022 04:30 PM America/Chicago Omer Reingold (Stanford) – Algorithmic Fairness, Loss Minimization and Outcome Indistinguishability Kent 107, 1020-24 East 58th St., Chicago, IL, 60637

Training a predictor to minimize a loss function fixed in advance is the dominant paradigm in machine learning. However, loss minimization by itself might fail to satisfy properties that come naturally in the context of algorithmic fairness. To remedy this, multi-group fairness notions such as multicalibration have been proposed, which require the predictor to share certain statistical properties of the ground truth, even when conditioned on a rich family of subgroups. These notions could be understood from the perspective of computational indistinguishability through the notion of outcome indistinguishability where a predictor can be viewed as giving a model of events that cannot be refused from empiric evidence within some computational bound. While differently motivated, this alternative paradigm for training predictors gives unexpected consequences, including: Practical methods for learning in a heterogeneous population, employed in the field to predict COVID-19 complications at a very early stage of the pandemic. A computational perspective on the meaning of individual probabilities. A rigorous new paradigm for loss minimization in machine learning, through the notion of omni predictors, that simultaneously applies to a wide class of loss-functions, allowing the specific loss function to be ignored at the time of learning. A method for adapting a statistical study on one probability distribution to another, which is blind to the target distribution at the time of inference and is competitive with wide-spread methods based on propensity scoring.

Based on a sequence of works joint with (subsets of) Cynthia Dwork, , Shafi Goldwasser, Parikshit Gopalan, Úrsula Hébert-Johnson, Adam Kalai, Christoph Kern, Michael P. Kim, Frauke Kreuter, Guy N. Rothblum, Vatsal Sharan, Udi Wieder, Gal Yona.


Omer Reingold

Rajeev Motwani Professor of Computer Science, Stanford University

Omer Reingold is the Rajeev Motwani professor of computer science at Stanford University and the director of the Simons Collaboration on the Theory of Algorithmic Fairness. Past positions include the Weizmann Institute of Science, Microsoft Research, the Institute for Advanced Study in Princeton, NJ, AT&Labs and Samsung Research America. His research is in the foundations of computer science and most notably in computational complexity, cryptography and the societal impact of computation. He is an ACM Fellow and a Simons Investigator. Among his distinctions are the 2005 Grace Murray Hopper Award and the 2009 Gödel Prize.

Related News & Events

UChicago CS News

UChicago London Colloquium Features Data Science, Quantum Research

Jul 01, 2022

Is it Ethical to Use Facial Imaging in Decision-Making?

Jun 28, 2022
UChicago CS News

Faculty Bill Fefferman and Chenhao Tan Receive Google Research Scholar Awards

Jun 21, 2022
UChicago CS News

Two Incoming UChicago CS PhD Students Receive Department of Energy Fellowship

Jun 16, 2022

Data Science Institute Summit

Jun 15, 2022
UChicago CS News

DSI Summer Lab Returns In-Person With 49 Students From Across the U.S.

Jun 14, 2022
UChicago CS News

First-Year PhD Student Co-Authors Outstanding Paper Award Winner at TQC 2022

Apr 28, 2022
UChicago CS News

UChicago CS Labs Join Museum of Science & Industry For Robot Block Party

Apr 20, 2022
UChicago CS News

Three UChicago CS Security Projects Receive Funding From Institute

Mar 25, 2022
UChicago CS News

Junchen Jiang Wins CAREER Award to Study Using ML to Optimize Video Experiences

Mar 24, 2022
UChicago CS News

New Data & Democracy Research Initiative Launched at University of Chicago

Mar 09, 2022
UChicago CS News

New Assistant Professor Rana Hanocka Combines AI, 3D, and Computer Graphics

Feb 09, 2022
arrow-down-largearrow-left-largearrow-right-large-greyarrow-right-large-yellowarrow-right-largearrow-right-smallbutton-arrowclosedocumentfacebookfacet-arrow-down-whitefacet-arrow-downPage 1CheckedCheckedicon-apple-t5backgroundLayer 1icon-google-t5icon-office365-t5icon-outlook-t5backgroundLayer 1icon-outlookcom-t5backgroundLayer 1icon-yahoo-t5backgroundLayer 1internal-yellowinternalintranetlinkedinlinkoutpauseplaypresentationsearch-bluesearchshareslider-arrow-nextslider-arrow-prevtwittervideoyoutube