Convergence of Stochastic Gradient Descent with mini-batching and infinite variance

Abstract

Stochastic gradient descent (SGD) with mini-batching is a standard tool in large-scale optimization, yet its theoretical properties under heavy-tailed gradient noise remain largely unexplored. In this paper we study SGD with increasing batch sizes when the gradient noise belongs to the domain of attraction of an $\hat{I}\pm$-stable law with $\hat{I}\pm \in (1,2)$. Building on existing results for the finite-variance regime and for heavy-tailed SGD without batching, we establish three main results. First, we derive $L^p$ moment bounds for the SGD error and show that increasing batch sizes lead to faster convergence rates. In particular, batching enables convergence in probability even for a constant stepsize. Second, we prove that the properly normalized SGD iterates converge in distribution to the stationary law of an Ornstein-Uhlenbeck process driven by an $\hat{I}\pm$-stable Lévy process. Third, for Polyak-Ruppert averaging we obtain a stable limit theorem with a normalization that explicitly depends on the batch-size schedule.

37 pages, 0 figures