Πλοήγηση Τμήμα Μαθηματικών και Στατιστικής / Department of Mathematics and Statistics ανά Συγγραφέα "Anastasiou, Andreas"
-
Article
Assessing the multivariate normal approximation of the maximum likelihood estimator from high-dimensional, heterogeneous data
Anastasiou, Andreas (2018)The asymptotic normality of the maximum likelihood estimator (MLE) under regularity conditions is a cornerstone of statistical theory. In this paper, we give explicit upper bounds on the distributional distance between the ...
-
Conference Object
Normal Approximation for Stochastic Gradient Descent via Non-Asymptotic Rates of Martingale CLT
Anastasiou, Andreas; Balasubramanian, Krishnakumar; Erdogdu, Murat A. (Proceedings of Machine Learning Research (PMLR), 2019)We provide non-asymptotic convergence rates of the Polyak-Ruppert averaged stochastic gradient descent (SGD) to a normal random vector for a class of twice-differentiable test functions. A crucial ...