Dr. Frederica Darema Lecture Series Presents "Tackling Bias and Uncertainty with Tractable Probabilistic Reasoning" by YooJung Choi
Speaker: YooJung Choi, assistant professor of computing and augmented intelligence, Arizona State University
Title: Tackling Bias and Uncertainty with Tractable Probabilistic Reasoning
Abstract: There is a growing demand to ensure that AI/ML systems are fair, robust, interpretable, and generally trustworthy. In this talk, I will discuss how tractable probabilistic reasoning and learning provide a framework for trustworthy AI. In particular, I will talk about our recent works on ensuring fairness in the presence of noise and bias in data, by explicitly representing the underlying distribution. This approach is enabled by probabilistic circuits, which are computational graphs that represent probability distributions and guarantee tractable inference of various queries. I will also discuss recent advancements in probabilistic circuits showcasing their future potential, such as divergences and optimal transport to compare and manipulate distributions.
Bio: YooJung Choi is an Assistant Professor in the School of Computing and Augmented Intelligence at Arizona State University. Her research interests lie in probabilistic machine learning, tractable probabilistic modeling and inference, knowledge representation and reasoning, as well as trustworthy artificial intelligence (algorithmic fairness, robustness, interpretability). Previously, she received her PhD in Computer Science at UCLA. She is the recipient of a research award from Cisco and a Simons-Berkeley Research Fellowship. She was selected for the AAAI 2023 New Faculty Highlights and the Rising Stars in EECS 2020 at UC Berkeley.
About the Dr. Frederica Darema Lecture Series:
Illinois Institute of Technology College of Computing’s Dr. Frederica Darema Lecture Series in Computer Science is funded by an endowment to help advance female and minority early-stage computer science researchers at U.S. academic institutions.
The lecture series is designed to encourage women and individuals from under-represented groups to pursue academic careers in computer sciences, and to focus on providing speaking opportunities for tenure track assistant professors (or the equivalent) at U.S. institutions in their fourth to sixth year. Lectureships may also be awarded to exceptional junior researchers in U.S. federal or industrial research laboratories in the third to fifth years of their careers, following doctoral/postdoctoral studies.