
We propose a fully online, Hessian-free debiased covariance estimator for SGD that achieves faster convergence.
Jan 1, 2026

Overfitting in high-dimensional imbalanced classification arises from truncation/skewing effects on the logit distribution.
Jan 1, 2026
Jan 1, 2023
Jan 1, 2022
Jan 1, 2020