Statistical Inference with Stochastic Gradient Algorithms
Tuning of stochastic gradient algorithms (SGAs) for optimization and sampling is often based on heuristics and trial-and-error rather than generalizable theory. We address this theory–practice gap by characterizing the statistical asymptotics of SGAs via a joint step-size–sample-size scaling limit. We show that iterate averaging with a large fixed step size is robust to the choice of tuning parameters and asymptotically has covariance proportional to that of the MLE sampling distribution. We also prove a Bernstein–von Mises-like theorem to guide tuning, including for generalized posteriors that are robust to model misspecification. Numerical experiments validate our results in realistic finite-sample regimes.
READ FULL TEXT