Proves uniform CLT for gradient flows in ERM and constructs an algorithm-aware, inversion-free covariance estimator for asymptotically valid time-uniform confidence intervals.
arXiv preprint arXiv:2410.16340 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Presents a self-normalized subsampling procedure for asymptotically valid confidence regions from SGD iterates under both finite and infinite variance assumptions.
citing papers explorer
-
Statistical Inference on Gradient Flows
Proves uniform CLT for gradient flows in ERM and constructs an algorithm-aware, inversion-free covariance estimator for asymptotically valid time-uniform confidence intervals.
-
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.