Want to create an interactive transcript for this episode?
Podcast: Arxiv Papers
Episode: [QA] Grokking at the Edge of Numerical Stability
Description:
This paper explores grokking in deep learning, linking delayed generalization to Softmax Collapse and proposing solutions to enable grokking without regularization through new activation functions and training algorithms.
https://arxiv.org/abs//2501.04697
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers