Combining random reshuffling and Richardson-Romberg extrapolation yields cubic bias refinement and better MSE for constant-step SGD on structured non-monotone variational inequalities.
Nonasymptotic analysis of stochastic gradient descent with the richardson- romberg extrapolation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
SGD on multiclass cross-entropy loss alternates between curvature-driven oscillations and stable regimes but self-stabilizes to enable best-iterate convergence with large learning rates for linear and two-layer models.
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
-
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.
-
SGD at the Edge of Stability: Stochastic Stabilization with Large Learning Rates
SGD on multiclass cross-entropy loss alternates between curvature-driven oscillations and stable regimes but self-stabilizes to enable best-iterate convergence with large learning rates for linear and two-layer models.
-
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.