Full Text Available

Note: Clicking the button above will open the full text document at the original institutional repository in a new window.

Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration

Saved in:
Bibliographic Details
Published in:Journal of Machine Learning Research
Format: Online Article RSS Article
Published: 2026
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864030190225588232
collection WordPress RSS
FRELIP Feed Integration
container_title Journal of Machine Learning Research
description
discipline_display Engineering & Technology
discipline_facet Engineering & Technology
format Online Article
RSS Article
genre Journal Article
id rss_article:4809
institution FRELIP
journal_source_facet Journal of Machine Learning Research
publishDate 2026
publishDateSort 2026
record_format rss_article
spellingShingle Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration
Computer Science & Information Science
Computer Science & IT
Engineering & Technology
sub_discipline_display Computer Science & IT
sub_discipline_facet Computer Science & IT
subject_display Computer Science & Information Science
Computer Science & IT
Engineering & Technology
Computer Science & Information Science
Computer Science & IT
Engineering & Technology
subject_facet Computer Science & Information Science
Computer Science & IT
Engineering & Technology
title Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration
title_auth Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration
title_full Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration
title_fullStr Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration
title_full_unstemmed Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration
title_short Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration
title_sort revisiting gradient normalization and clipping for nonconvex sgd under heavy-tailed noise: necessity, sufficiency, and acceleration
topic Computer Science & Information Science
Computer Science & IT
Engineering & Technology
url http://jmlr.org/papers/v26/24-1991.html