@article{understandingtheroleofmomentuminnon, title = {Momentum via Primal Averaging: Theoretical Insights and Learning Rate Schedules for Non-Convex Optimization}, author = {Aaron Defazio}, year = {2020}, eprint = {2010.00406}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2010.00406v4}, }