Learning Rates for Stochastic Gradient Descent With Nonconvex Objectives
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Transactions on Pattern Analysis and Machine Intelligence"
DOI: 10.1109/tpami.2021.3068154
Abstract: Stochastic gradient descent (SGD) has become the method of choice for training highly complex and nonconvex models since it can not only recover good solutions to minimize training errors but also generalize well. Computational and… read more here.
Keywords: nonconvex; stochastic gradient; learning rates; gradient descent ... See more keywords