Speaker: Micah Goldblum, Columbia University
Title: "Bridging the gap between deep learning theory and practice"
Abstract: Despite the widespread proliferation of neural networks, the mechanisms through which they operate so successfully are not well understood. In this talk, we will first explore empirical and theoretical investigations into neural network training and generalization and what they can tell us about why deep learning works. Then, we will examine a recent line of work on algorithm learning. While neural networks typically excel at pattern matching tasks, we consider whether neural networks can learn algorithms that scale to problem instances orders of magnitude larger than those seen during training.
Bio: Micah Goldblum is an assistant professor in the Department of Electrical Engineering at Columbia University. His research focuses on deep learning, especially on building safe AI systems and also using mathematical tools to understand how and why deep learning works. Micah’s research portfolio includes award winning work in Bayesian inference, generalization theory, algorithmic reasoning, and AI security, privacy, and fairness. Micah’s work appears at venues like NeurIPS, ICLR, ICML, and CVPR. In 2022, he received the ICML Outstanding Paper Award. Before his current position, Micah was a postdoctoral research fellow at New York University with Yann LeCun and Andrew Gordon Wilson before which he received a Ph.D. in mathematics at the University of Maryland under Tom Goldstein and Wojciech Czaja
This talk will be offered in a hybrid format. If you wish to participate remotely, please send an email to [email protected].
