Presents a self-normalized subsampling procedure for asymptotically valid confidence regions from SGD iterates under both finite and infinite variance assumptions.
Stochastic differential equations models for least-squares stochastic gradient descent.arXiv preprint arXiv:2407.02322, 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.