Date: Wednesday, March 12th, 2025
9:00 am – 10:00 am Pacific Time
12:00 pm – 1:00 pm Eastern Time
Location: Weekly Seminar, Zoom
Title: Responsible Learning with Quantile-Based Risk Measures
Abstract:
Modern digital systems powered by machine learning have permeated various aspects of society, playing an instrumental role in many high-stakes areas such as medical care and finance. Therefore, it is crucial to ensure that machine learning algorithms are deployed in a “responsible” way so that digital systems are more reliable, explainable, and aligned with societal values. In this talk, I will introduce my research on building practical theories to guide real-world responsible deployment of machine learning. First, I will introduce our work on distribution-free uncertainty quantification for a rich class of statistical functionals of quantile functions to avoid catastrophic outcomes and unfair discrimination in the deployment of black-box models. The power of this framework is shown by applications to large language models and medical care. Second, I will briefly describe our recent work regarding autoevalution of models under quantile-based risk measures.
Bio:
Zhun Deng is an assistant professor at the University of North Carolina at Chapel Hill. He is currently a postdoctoral researcher with Toniann Pitassi and Richard Zemel at Columbia University. Previously, he completed his Ph.D. from the Theory of Computation Group at Harvard University, where he was advised by Cynthia Dwork. His research interests lie at the intersection of machine learning, statistics, and theoretical computer science. His current interests are mainly in building practical frameworks with theoretical guarantees to address cutting-edge issues regarding reliable learning and responsible computing.