Sampling and Update Frequencies in Proximal Variance-Reduced Stochastic Gradient Methods

M Morin, P Giselsson - arXiv preprint arXiv:2002.05545, 2020 - arxiv.org
Variance-reduced stochastic gradient methods have gained popularity in recent times.
Several variants exist with different strategies for the storing and sampling of gradients and …

[HTML][HTML] Cocoercivity, smoothness and bias in variance-reduced stochastic gradient methods

M Morin, P Giselsson - Numerical Algorithms, 2022 - Springer
With the purpose of examining biased updates in variance-reduced stochastic gradient
methods, we introduce SVAG, a SAG/SAGA-like method with adjustable bias. SVAG is …

Stochastic forward-backward-half forward splitting algorithm with variance reduction

L Qin, Y Zhang, QL Dong - arXiv e-prints, 2023 - ui.adsabs.harvard.edu
In this paper, we present a stochastic forward-backward-half forward splitting algorithm with
variance reduction for solving the structured monotone inclusion problem composed of a …

[PDF][PDF] ББК 22.17 я73 Г22

АВ Гасников - labmmo.ru
Данное пособие написано по материалам лекций, прочитанных автором в летней
школе «Современная математика» в Ратмино (г. Дубна) в июле 2017 г. Идея курса …

[PDF][PDF] Paper I

PVR Stochastic - Fixed Point Iterations for Finite Sum Monotone …, 2022 - lucris.lub.lu.se
Variance-reduced stochastic gradient methods have gained popularity in recent times.
Several variants exist with different strategies for the storing and sampling of gradients and …