Attend LIONS seminar with guest Martina Cardone, April 24

Join the Learning, Information, Optimization, Networks and Statistics, or LIONS, group for a seminar with Martina Cardone, associate professor with the Department of Electrical and Computer Engineering at the University of Minnesota. An NSF CAREER Award recipient, Cardone’s research aims to develop theoretical frameworks that offer engineering guidelines and insights for the study of practically relevant problems and to design of computationally feasible techniques aimed to achieve the fundamental theoretical performance limits as close as possible.

Focal loss has emerged as a de facto training loss in class-imbalanced classification problems, especially in computer vision. Despite its empirical success, its theoretical properties and benefits have not been well explored. In this talk, we investigate several information-theoretic aspects of focal loss, including its connection to relative entropy and the emergence of novel information measures it induces. These results, which are also experimentally validated, provide a theoretical foundation for understanding focal loss and help clarify the trade-offs it introduces when applied to imbalanced learning tasks. We also propose the focal loss as a distortion measure for lossy source coding and discuss some research directions that are the object of current investigation.

Visit the LIONS Seminar website for more information.

LIONS Seminar: Focal Loss: An Information-Theoretical Perspective
Friday, April 24, 2026
1:30–2:30 p.m.
Goldwater Center (GWC) 487, Tempe campus [map]
Attend online via Zoom