-
HDSI Seminar Series: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate by Quanquan Gu
HDSI Seminar Series: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate by Quanquan Gu
Title: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate HDSI Seminar Series Quanquan Gu, Assistant Professor of Computer Science at UCLA Abstract: Understanding the algorithmic bias of stochastic gradient descent (SGD) is one of the key challenges in modern machine learning and deep learning theory. Most of the existing works, however, focus […]