New in-expectation convergence guarantees for SMD, ASMD (convex) and SGD, SGDM (nonconvex) under heavy-tailed noise without bounded-domain restrictions or algorithmic modifications.
Can SGD Handle Heavy-Tailed Noise?
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
math.OC 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Proximal stochastic spectral preconditioning converges for nonconvex constrained objectives under heavy-tailed noise, with a variance-reduced version achieving faster rates and a refined analysis of Muon iterations.
citing papers explorer
-
In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise
New in-expectation convergence guarantees for SMD, ASMD (convex) and SGD, SGDM (nonconvex) under heavy-tailed noise without bounded-domain restrictions or algorithmic modifications.
-
Constrained Stochastic Spectral Preconditioning Converges for Nonconvex Objectives
Proximal stochastic spectral preconditioning converges for nonconvex constrained objectives under heavy-tailed noise, with a variance-reduced version achieving faster rates and a refined analysis of Muon iterations.