A self-normalized subsampling method builds asymptotically valid confidence regions for Polyak–Ruppert averaged SGD under finite- or infinite-variance gradient noise.
H., Richard, G., and Sagun, L
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
Increasing mini-batch sizes in SGD under alpha-stable heavy-tailed noise yield improved L^p convergence rates, convergence in probability with constant stepsizes, and explicit stable distributional limits for the iterates and Polyak-Ruppert averages.
citing papers explorer
-
Statistical Inference for Stochastic Gradient Descent: Beyond Finite Variance
A self-normalized subsampling method builds asymptotically valid confidence regions for Polyak–Ruppert averaged SGD under finite- or infinite-variance gradient noise.
-
Convergence of Stochastic Gradient Descent with mini-batching and infinite variance
Increasing mini-batch sizes in SGD under alpha-stable heavy-tailed noise yield improved L^p convergence rates, convergence in probability with constant stepsizes, and explicit stable distributional limits for the iterates and Polyak-Ruppert averages.