Improved batch-means rates for SGD covariance estimation plus a minimax-optimal trajectory-regression estimator achieving Θ(n^{-(1-α)/2}) for Hessian-free inference.
Statistical inference for online learning and stochastic approximation via hierarchical incremental gradient descent
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Combining random reshuffling and Richardson-Romberg extrapolation yields cubic bias refinement and better MSE for constant-step SGD on structured non-monotone variational inequalities.
citing papers explorer
-
Online Covariance Estimation in Averaged SGD: Improved Batch-Mean Rates and Minimax Optimality via Trajectory Regression
Improved batch-means rates for SGD covariance estimation plus a minimax-optimal trajectory-regression estimator achieving Θ(n^{-(1-α)/2}) for Hessian-free inference.
-
Shuffling the Data, Stretching the Step-size: Sharper Bias in constant step-size SGD
Combining random reshuffling and Richardson-Romberg extrapolation yields cubic bias refinement and better MSE for constant-step SGD on structured non-monotone variational inequalities.