arXiv:2604.21203v1 Announce Type: new Abstract: We study online inference and asymptotic covariance estimation for the stochastic gradient descent (SGD) algorithm. While classical methods (such as plug-in and batch-means estimators) are available, they either require inaccessible second-order (Hessian) information or suffer from slow convergence. To address these challenges, we propose a novel, fu
Refining Covariance Matrix Estimation in Stochastic Gradient Descent Through Bias Reduction
Ziyang Wei, Wanrong Zhu, Jingyang Lyu, Wei Biao Wu·arXiv stat.ML··1 min read
a
Continue reading on arXiv stat.ML
This article was sourced from arXiv stat.ML's RSS feed. Visit the original for the complete story.