Central limit theorems for stochastic gradient descent with averaging for stable manifolds
Central limit theorems for stochastic gradient descent with averaging for stable manifolds
In this article, we establish new central limit theorems for Ruppert-Polyak averaged stochastic gradient descent schemes. Compared to previous work we do not assume that convergence occurs to an isolated attractor but instead allow convergence to a stable manifold. On the stable manifold the target function is constant and the …