Machine learning in Madrid    (zoom)

Lunes, 14 de febrero de 2022, 11:30-12:30h  (horario diferente al habitual!!!!)

Enlace:  https://us06web.zoom.us/j/82533032803?pwd=Qm41WXVSUlRDQ0lIbnZUM0dMY05WZz09

Ponente:   Vivak Patel (UW-Madison)

Título:  Global Convergence and Stability of Stochastic Gradient Descent

Abstract: Stochastic gradient descent (SGD) is widely deployed in a number of different disciplines, often on non-convex problems with complicated noise models. However, SGD's existing convergence theory often does not apply. In this talk, we will establish the need for a convergence theory under broader assumptions with some simple examples. We will then state a global convergence result for SGD under these broad assumptions. Then, we will discuss the issue of stability, which addresses what happens when SGD's iterates diverge.