A self-normalized subsampling method builds asymptotically valid confidence regions for Polyak–Ruppert averaged SGD under finite- or infinite-variance gradient noise.
Online Bootstrap Inference with Noncon- vex Stochastic Gradient Descent Estimator
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
stat.ML 5representative citing papers
Establishes non-asymptotic Gaussian approximation bounds for federated LSA with explicit communication-heterogeneity trade-offs and introduces an online multiplier bootstrap for last-iterate inference with validity guarantees.
Develops a batch-free online covariance estimator for sketched Newton methods, proves its consistency, and demonstrates use for online statistical inference on regression and CUTEst problems.
A novel bias-reduced online covariance estimator for SGD achieves convergence rate n to the power (α-1)/2 times square root of log n without second-order derivatives.
Proves the first fully non-asymptotic bound on the accuracy of multiplier bootstrap for constructing confidence sets from Polyak-Ruppert SGD iterates, achieving convex-distance rates up to 1/sqrt(n) under regularity conditions.
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.
-
Gaussian Approximation and Multiplier Bootstrap for Federated Linear Stochastic Approximation
Establishes non-asymptotic Gaussian approximation bounds for federated LSA with explicit communication-heterogeneity trade-offs and introduces an online multiplier bootstrap for last-iterate inference with validity guarantees.
-
Online Covariance Matrix Estimation in Sketched Newton Methods
Develops a batch-free online covariance estimator for sketched Newton methods, proves its consistency, and demonstrates use for online statistical inference on regression and CUTEst problems.
-
Refining Covariance Matrix Estimation in Stochastic Gradient Descent Through Bias Reduction
A novel bias-reduced online covariance estimator for SGD achieves convergence rate n to the power (α-1)/2 times square root of log n without second-order derivatives.
-
Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent
Proves the first fully non-asymptotic bound on the accuracy of multiplier bootstrap for constructing confidence sets from Polyak-Ruppert SGD iterates, achieving convex-distance rates up to 1/sqrt(n) under regularity conditions.