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.
arXiv preprint arXiv:2306.02205 , year=
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
-
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.