Talkboctopus Seminar Series: S4 Episode 5: Juan Carlos Perdomo

Abstract: When algorithmic predictions are used to inform social decision-making, these predictions don’t just forecast the world around it: they actively shape it. From online recommender platforms to financial predictions, machine learning systems are in active feedback with the surrounding environment and have the ability to steer the underlying data distributions toward different targets. While traditionally neglected, these causal forces of prediction have been recently formalized in a new risk minimization framework called performative prediction.

Following a brief overview of the performative prediction framework, in this talk, I will present some work that directly tries to address the distinction between forecasting future outcomes and steering data distributions toward socially desirable targets. Building upon a new line of research in supervised learning, we introduce the idea of performative omnipredictors. These are simple predictive models that simultaneously encode the optimal decision rule with respect to many possibly-competing objectives. As part of our presentation, we will discuss some connections with the outcome indistinguishability literature and illustrate how the solution concepts we introduce enable decision-makers to flexibly decide on the goals of prediction in performative settings.

Bio: Juan Carlos Perdomo is a graduate student in Computer Science at the University of California, Berkeley, where he is co-advised by Moritz Hardt and Peter Bartlett. Before coming to Berkeley, he did his undergrad in computer science and mathematics at Harvard where he worked with Yaron Singer. He is interested in the foundations of machine learning. Before becoming interested in research, he was part of the Puerto Rican national team in sailing.