AI RESEARCH
Statistical Inference for Stochastic Gradient Descent Beyond Finite Variance
arXiv CS.LG
•
ArXi:2605.26000v1 Announce Type: cross Stochastic gradient descent (SGD) is a foundational algorithm for large-scale statistical learning and stochastic optimization. However, statistical inference based on SGD iterates remains challenging when stochastic gradients have infinite variance, as the relevant limiting distributions depend on unknown nuisance parameters. In this paper, we develop an efficient, model-agnostic methodology for constructing confidence regions from SGD trajectories that applies in both finite- and infinite-variance regimes.