Strong Gaussian Approximation of Constant Learning Rate SGD: Bias and Trajectory Inference

Joseph Keslin, Wei Biao Wu

This paper develops strong Gaussian approximations (KMT type) for constant learning rate stochastic gradient descent (SGD). We work with heavy tailed noise and assume that the number of iterates grows and the learning rate shrinks simultaneously. Our work constructs simple Gaussian processes on the same space and bounds, in probability, the maximum difference between the SGD errors and their respective limits. While there exist central limit theorems for constant rate SGD centered at the optimum, these only provide individual iterate inference. By contrast, our quenched KMT approximations allow for finite sample, simultaneous, whole-trajectory-level inference and imply stochastic process convergence (Functional Central Limit Theorems (FCLTs)). For accumulated errors centered at the true optimum, we first obtain a KMT-type approximation bound when the learning rate scales as $γ_n=\frac{c}{\sqrt n}+o(n^{-1/2})$ for a constant $c \in \mathbb{R}^+$ and $n$ iterations. The result reveals a trade off between controlling the bias of SGD and the initialization effect, with no learning rate scaling generally making both contributions vanish in the accumulated error limit. To eliminate…