Presents a self-normalized subsampling procedure for asymptotically valid confidence regions from SGD iterates under both finite and infinite variance assumptions.
Limit theorems for stochastic gradient descent with infinite variance.arXiv preprint arXiv:2410.16340, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Statistical Inference for Stochastic Gradient Descent Beyond Finite Variance
Presents a self-normalized subsampling procedure for asymptotically valid confidence regions from SGD iterates under both finite and infinite variance assumptions.