DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule Paper • 2302.12022 • Published Feb 8, 2023 • 1
Lion Secretly Solves Constrained Optimization: As Lyapunov Predicts Paper • 2310.05898 • Published Oct 9, 2023 • 2
When, Why and How Much? Adaptive Learning Rate Scheduling by Refinement Paper • 2310.07831 • Published Oct 11, 2023 • 1
Stochastic model-based minimization of weakly convex functions Paper • 1803.06523 • Published Mar 17, 2018
Handbook of Convergence Theorems for (Stochastic) Gradient Methods Paper • 2301.11235 • Published Jan 26, 2023