Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions

Tao Sun, Qingsong Wang, Dongsheng Li 0001, Bao Wang. Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions. In Andreas Krause 0001, Emma Brunskill, KyungHyun Cho, Barbara Engelhardt, Sivan Sabato, Jonathan Scarlett, editors, International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA. Volume 202 of Proceedings of Machine Learning Research, pages 33077-33099, PMLR, 2023. [doi]

Abstract

Abstract is missing.