Newsroom
foundation models
-
S&DS Seminar: Jingfeng Wu (Berkeley), “Gradient Descent Dominates Ridge: A Statistical View on Implicit Regularization”
Talk summary: A key puzzle in deep learning is how simple gradient methods find generalizable solutions without explicit regularization. This talk discusses the implicit regularization of gradient descent (GD) through the lens of statistical dominance. Using least squares as a clean proxy, we present two surprising findings. First, GD dominates ridge regression. For any well-specified…
-
S&DS Seminar: Alex Damian (Princeton), “Learning From Gaussian Data: Single and Multi-Index Models”
Abstract: In this work we consider generic Gaussian Multi-index models, in which the labels only depend on the (Gaussian) d-dimensional inputs through their projection onto a low-dimensional subspace, and we study efficient agnostic estimation procedures for this hidden subspace. We introduce the generative leap exponent k*, a natural extension of the generative exponent from [DPVLB24] to…
-
Lu & Tassiulas awarded DOE funding for artificial intelligence research
The Lu Group (Professor Lu Lu, Department of Statistics and Data Science and member of FDS) has been awarded a new $4 Million grant from the US Department of Energy’s Advanced Scientific Computing Research Program (DOE ASCR) as the Lead to develop physics-informed and energy-aware federated learning of neural multi-operator learners as scientific foundation models, in…
-
FDS Colloquium: Quanquan C. Liu, “Massive Graph Algorithms from Theory to Practice and Back”
“Massive Graph Algorithms from Theory to Practice and Back” Abstract: In the face of massive graph data, there is increased interest in developing novel algorithmic foundations for practical graph algorithms that are scalable, efficient, and private. Algorithm designers face many challenges when creating algorithms for real-world deployment. First, modern datasets often reach sizes of hundreds…
-
-
