TILOS - OPTML++ Seminar Series

Mert Pilanci, Stanford University Abstract: Since deep neural network training problems are inherently non-convex, their recent dramatic success largely relies on non-convex optimization heuristics and experimental findings. Despite significant advancements, the non-convex nature of neural network training poses two central challenges: first, understanding the underlying mechanisms that contribute to model performance, and second, achieving efficient […]

Masashi Sugiyama, University of Tokyo and RIKEN Abstract: In statistical inference and machine learning, we face a variety of uncertainties such as training data with insufficient information, label noise, and bias. In this talk, I will give an overview of our research on reliable machine learning, including weakly supervised classification (positive unlabeled classification, positive confidence classification, […]

Marco Mondelli, Institute of Science and Technology Austria Abstract: A recent line of work has analyzed the properties of deep over-parameterized neural networks through the lens of the Neural Tangent Kernel (NTK). In this talk, I will show how concentration bounds on the NTK (and, specifically, on its smallest eigenvalue) provide insights on (i) the […]