Tight Dimension Independent Lower Bound on the Expected Convergence Rate for Diminishing Step Sizes in SGD

PHUONG_HA NGUYEN, Lam Nguyen, Marten van Dijk

Nov-19-2025, 06:01:07 GMT–Neural Information Processing Systems 

We study the convergence of Stochastic Gradient Descent (SGD) for strongly convex objective functions.