Optimization for ML and AI Seminar: A non-equilibrium phase transition with broken ergodicity leads to double descent and benign overfitting in machine learning

HDSI 123 and Virtual 3234 Matthews Ln, La Jolla, CA, United States

Nigel Goldenfeld, UC San Diego Department of Physics and HDSI Abstract: The remarkable ability of modern neural networks to generalize improves with increasing network capacity, even when the number of model parameters or effective degrees of freedom exceeds the number of training data points. This phenomenon is all the more surprising given that generalization error […]

CVPR 2026 Workshop: Trustworthy, Robust, Uncertainty-Aware, and Explainable Visual Intelligence and Beyond (TRUE-V)

IEEE/CVF Conference on Computer Vision and Pattern Recognition Denver, CO, United States

Contemporary vision models and vision–language models are increasingly deployed in high-stakes domains, yet remain opaque, fragile, and difficult to align across tasks and modalities. This workshop aim to foster dialogue on the urgent need for transparent, reliable, and safe computer vision systems, especially in critical domains such as healthcare, transportation, and legal decision making. It brings together […]

TILOS-SDSU Seminar: Distributionally Robust Optimization and Applications to Air Traffic Management

Lamden Hall (LH) 247 San Diego State University, San Diego, CA, United States

Max Z. Li, University of Michigan Abstract: Ground Delay Programs (GDPs) mitigate air traffic demand-capacity imbalances by holding flights on the ground at their origin airports when the destination airport's arrival capacity is reduced, thereby limiting costly airborne holding. A central challenge is that day-to-day demand-capacity balancing depends on accurate capacity predictions. In practice, however, […]

Vernor Vinge Lecture Series on the Future of AI and Society with Ted Chiang: No Machine Has Passed the Turing Test

Halicioglu Data Science Institute Room 123 3234 Matthews Ln, La Jolla, CA, United States

It's now commonly asserted that the Turing Test is no longer a useful metric because current LLMs easily pass it. In this talk, Ted Chiang will offer a different interpretation of Turing's paper and what Turing actually meant by a thinking machine. Linguistic fluency of the type that Turing described is a very high bar, […]