Lookahead Optimizer: k steps forward, 1 step back | Michael Zhang

A talk from the Toronto Machine Learning Summit: The video is hosted by About the speaker: Michael Zhang is a PhD student at the University of Toronto and Vector Institute, supervised by Jimmy Ba. His current research focus is on optimization and deep learning. He was previously at UC Berkeley, where he did research in reinforcement learning and robotics in Pieter Abbeel’s group. About the talk: The vast majority of successful deep n