Theoretical Foundations: From the Early Days of Neural Networks to the Modern Deep Learning Era

This workshop celebrates Professor Peter Bartlett's 60th birthday. From his pioneering research on the generalization ability of neural networks in the 1990s to his recent efforts to rigorously understand phenomena such as benign overfitting in deep learning, Peter has been at the forefront of theoretical developments in machine learning for over three decades. As associate director of the Simons Institute from 2017 to 2022, he facilitated numerous workshops that advanced foundational work in areas such as data science, deep learning, machine learning, reinforcement learning, and statistical inference. This workshop brings together both established researchers and emerging leaders to reflect on the past achievements of machine learning theory and to help shape its future.