Applied Math Seminar: Michael Murray (UCLA)
Estella 1021 (Emmy Noether Room), Pomona College Claremont, CA, United StatesTitle: Towards Understanding the Success of First Order Methods in Training Mildly Overparameterized Networks Abstract: For most problems of interest the loss landscape of a neural network is non-convex and contains a plethora of spurious critical points. Despite this first order methods such as SGD and Adam are in practice remarkably successful at finding optimal, […]