Full Text Available

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

Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory

Saved in:
Bibliographic Details
Published in:ArXiv cs.AI Recent Papers
Format: Online Article RSS Article
Published: 2026
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1865127356560048129
collection WordPress RSS
FRELIP Feed Integration
container_title ArXiv cs.AI Recent Papers
description
discipline_display Engineering & Technology
discipline_facet Engineering & Technology
format Online Article
RSS Article
genre Journal Article
id rss_article:51529
institution FRELIP
journal_source_facet ArXiv cs.AI Recent Papers
publishDate 2026
publishDateSort 2026
record_format rss_article
spellingShingle Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory
ArXiv cs.AI Recent Papers
Chemical Engineering
Engineering & Technology
sub_discipline_display Chemical Engineering
sub_discipline_facet Chemical Engineering
subject_display ArXiv cs.AI Recent Papers
Chemical Engineering
Engineering & Technology
ArXiv cs.AI Recent Papers
Chemical Engineering
Engineering & Technology
subject_facet ArXiv cs.AI Recent Papers
Chemical Engineering
Engineering & Technology
title Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory
title_auth Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory
title_full Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory
title_fullStr Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory
title_full_unstemmed Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory
title_short Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory
title_sort detecting overfitting in neural networks during long-horizon grokking using random matrix theory
topic ArXiv cs.AI Recent Papers
Chemical Engineering
Engineering & Technology
url https://arxiv.org/abs/2605.12394v1