Grokking at the edge of linear separability (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Grokking at the edge of linear separability

First screen, captured 2 years ago.

Looks similar

Screenshot of arxiv.org: Optimizing ML training with metagradient descent

Optimizing ML training with metagradient descent (arxiv.org)

79 points by ladberg 1 year ago | 13 comments

Screenshot of arxiv.org: Grokfast: Accelerated Grokking by Amplifying Slow Gradients

Grokfast: Accelerated Grokking by Amplifying Slow Gradients (arxiv.org)

104 points by johnsutor 2 years ago | 31 comments

Screenshot of arxiv.org: Provable Scaling Laws of Feature Emergence from Learning Dynamics of Grokking

Provable Scaling Laws of Feature Emergence from Learning Dynamics of Grokking (arxiv.org)

20 points by sva_ 1 year ago | 0 comments

Screenshot of arxiv.org: Machine Learnability as a Measure of Order in Aperiodic Sequences

Machine Learnability as a Measure of Order in Aperiodic Sequences (arxiv.org)

41 points by PaulHoule 1 year ago | 4 comments

Screenshot of arxiv.org: Large Language Models as Markov Chains

Large Language Models as Markov Chains (arxiv.org)

63 points by Anon84 1 year ago | 33 comments

Screenshot of arxiv.org: A Theory on Adam Instability in Large-Scale Machine Learning

A Theory on Adam Instability in Large-Scale Machine Learning (arxiv.org)

129 points by vov_or 3 years ago | 47 comments