Consequential decisions compel individuals to react in response to the specifics of the decision rule. This individual-level response in aggregate can disrupt the statistical patterns that motivated the decision rule, leading to unforeseen consequences.
In this talk, I will discuss two ways to formalize dynamic decision making problems. One, called performative prediction, makes macro-level assumptions about the aggregate population response to a decision rule. The other, called strategic classification, follows microeconomic theory in modeling individuals as utility-maximizing agents with perfect information. We will see key results and limitations of either approach. Drawing on lessons from the microfoundations project in economics, I will outline a viable middleground between the two.
Bio: Moritz Hardt is an Assistant Professor in the Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley. Hardt investigates algorithms and machine learning with a focus on reliability, validity, and societal impact. After obtaining a PhD in Computer Science from Princeton University, he held positions at IBM Research Almaden, Google Research and Google Brain. Hardt is a co-founder of the Workshop on Fairness, Accountability, and Transparency in Machine Learning (FAT/ML) and a co-author of the forthcoming textbook "Fairness and Machine Learning". He has received an NSF CAREER award, a Sloan fellowship, and best paper awards at ICML 2018 and ICLR 2017.