A Nonlinear Time-Series Theory for Constant-step SGD with Momentum
arXiv:2610.16034v1 Announce Type: new Abstract: Constant-step stochastic gradient descent with momentum (SGDM) augments the parameter recursion with a momentum state that carries geometrically decaying memory of past stochastic gradients. We study this coupled recursion as a nonlinear time series a…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-14 04:00 · arXiv stat.ML
A Nonlinear Time-Series Theory for Constant-step SGD with Momentum