24 citations · 68 across the 23 of their papers we have counts for
29 papers
Analysing heavy-tail properties of Stochastic Gradient Descent by means of Stochastic Recurrence Equations
Ewa Damek, Sebastian Mentemeier
In recent works on the theory of machine learning, it has been observed that heavy tail properties of Stochastic Gradient Descent (SGD) can be studied in the probabilistic framewor…
Whittle estimation based on the extremal spectral density of a heavy-tailed random field
Ewa Damek, Thomas Mikosch, Yuwei Zhao +1
We consider a strictly stationary random field on the two-dimensional integer lattice with regularly varying marginal and finite-dimensional distributions. Exploiting the regular v…
Tails of bivariate stochastic recurrence equation with triangular matrices
Ewa Damek, Muneya Matsui
We study bivariate stochastic recurrence equations with triangular matrix coefficients and we characterize the tail behavior of their stationary solutions . Rec…
Stochastic recurrence equation with diagonal matrices
Ewa Damek
Multivariate process satisfying affine stochastic recurrence equation with generic diagonal matrices is considered. We prove that the stationary solution is regularly varying. The…
Limit theorems for supercritical branching processes in random environment
Dariusz Buraczewski, Ewa Damek
We consider the branching process in random environment , which is a~population growth process where individuals reproduce independently of each other with the r…
A renewal theorem and supremum of a perturbed random walk
Ewa Damek, Bartosz Kołodziejek
We study tails of the supremum of a perturbed random walk under regime which was not yet considered in the literature. Our approach is based on a new renewal theorem, which is of i…