arXiv stat.ML August 3, 2026 · Papers

Statistical Inference for Stochastic Gradient Descent: Beyond Finite Variance

arXiv:2605.26000v2 Announce Type: replace Abstract: Stochastic gradient descent (SGD) is foundational to large-scale statistical learning and stochastic optimization. However, in some modern statistical learning problems, stochastic gradients can exhibit infinite-variance behavior. Consequently, classical inference met