CFCS Distinguished Lectures

On Learning in the Presence of Biased Data and Strategic Behavior

  • Prof. Avrim Blum, TTIC
  • Time: 2021-12-17 10:00
  • Host: Dr. Yuqing Kong
  • Venue: Online Talk


In this talk I will discuss two lines of work involving learning in the presence of biased data and strategic behavior. In the 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. In the second line of work 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.


Avrim Blum received his BS, MS, and PhD from MIT in 1987, 1989, and 1991 respectively.  He then served on the faculty in the Computer Science Department at Carnegie Mellon University from 1992 to 2017. In 2017 he joined the Toyota Technological Institute at Chicago as Chief Academic Officer.

Prof. Blum's main research interests are in Theoretical Computer Science and Machine Learning, including Machine Learning Theory, Algorithmic Game Theory, Algorithmic Fairness, and non-worst-case analysis of algorithms. He is currently working on fairness and incentive issues in machine learning, learning systems that know when they don't know, and robustness guarantees in the presence of adversarial attacks. He has served as Program Chair for the IEEE Symposium on Foundations of Computer Science (FOCS), the Innovations in Theoretical Computer Science Conference (ITCS), and the Conference on Learning Theory (COLT).  He has served as Chair of the ACM SIGACT Committee for the Advancement of Theoretical Computer Science and on the SIGACT Executive Committee.  Blum is recipient of the AI Journal Classic Paper Award, the ICML/COLT 10-Year Best Paper Award, the Sloan Fellowship, the NSF National Young Investigator Award, and the Herbert Simon Teaching Award, and he is a Fellow of the ACM.


  • Admmission


  • Live