@inproceedings{NEURIPS2022_3c215225, author = {Li, Zhiyuan and Wang, Tianhao and Yu, Dingli}, booktitle = {Advances in Neural Information Processing Systems}, editor = {S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh}, pages = {9233--9248}, publisher = {Curran Associates, Inc.}, title = {Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay}, url = {https://proceedings.neurips.cc/paper_files/paper/2022/file/3c215225324f9988858602dc92219615-Paper-Conference.pdf}, volume = {35}, year = {2022} }