Paper ID: 2303.16502

Unified analysis of SGD-type methods

Eduard Gorbunov

This note focuses on a simple approach to the unified analysis of SGD-type methods from (Gorbunov et al., 2020) for strongly convex smooth optimization problems. The similarities in the analyses of different stochastic first-order methods are discussed along with the existing extensions of the framework. The limitations of the analysis and several alternative approaches are mentioned as well.

Submitted: Mar 29, 2023