@article {2102.13653, archivePrefix = {arXiv}, eprint = {2102.13653}, primaryClass = {cs.LG}, author = {Ali Ramezani-Kebrya and Ashish Khisti and Ben Liang}, title = {On the Generalization of Stochastic Gradient Descent with Momentum}, year = {2021}, url = {http://arxiv.org/abs/2102.13653} }