Large Spikes in Stochastic Gradient Descent: A Large-Deviations View

MaRDI QIDQ7221824arXivFDO

Authors Benjamn Gess, Daniel Heydecker

Publication date 2026

Published in arXiv

Mathematics Subject Classification ID

Random dynamical systems aspects of multiplicative ergodic theory, Lyapunov exponents (37H15) Large deviations (60F10) Discrete-time Markov processes on general state spaces (60J05) Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05)

arXiv classification

cs.LG

This page was built for publication: Large Spikes in Stochastic Gradient Descent: A Large-Deviations View

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7221824)