Avrim Blum
CS Distinguished Lecture Series
September 15, 2022
11:00 AM - 12:15 PM
Learning in the Presence of Biased Data and Strategic Behavior
Presenter: Avrim Blum, Toyota Technological Institute at Chicago (TTIC)
Abstract: In this talk, I will discuss two lines of work involving learning in the presence of biased data and strategic behavior. First, we ask whether fairness constraints on learning algorithms can actually improve the accuracy of the classifier produced, when training data is unrepresentative or corrupted due to bias. Typically, fairness constraints are analyzed as a tradeoff with classical objectives such as accuracy. Our results here show there are natural scenarios where they can be a win-win, helping to improve overall accuracy. Second, we consider strategic classification: settings where the entities being measured and classified wish to be classified as positive (e.g., college admissions) and will try to modify their observable features if possible to make that happen. We consider this in the online setting where a particular challenge is that updates made by the learning algorithm will change how the inputs behave as well.
Speaker Bio: Avrim Blum is professor and chief academic officer at the Toyota Technological Institute at Chicago; he was previously a faculty member at Carnegie Mellon University for 25 years. His main research interests are in machine learning theory, algorithmic game theory, and algorithmic fairness. He has served as program chair for the Conference on Learning Theory (COLT), the IEEE Symposium on Foundations of Computer Science (FOCS), and the Innovations in Theoretical Computer Science Conference (ITCS). Blum is recipient of the AI Journal Classic Paper Award, the ICML/COLT 10-Year Best Paper Award, the ACM Paris Kanellakis Award, the Sloan Fellowship, the NSF National Young Investigator Award, and the Herbert Simon Teaching Award. He is also a Fellow of the ACM.
This lecture may also be attended remotely, via Zoom.
Faculty host: Xiaorui Sun
Date posted
Sep 15, 2022
Date updated
Sep 15, 2022