Gradients are not all you need (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Gradients are not all you need

First screen, captured 3 years ago.

Looks similar

Screenshot of arxiv.org: Every model learned by gradient descent is approximately a kernel machine (2020)

Every model learned by gradient descent is approximately a kernel machine (2020)(arxiv.org)

157 points by Anon84 2 years ago | 111 comments

Screenshot of arxiv.org: Grande: Gradient-Based Decision Tree Ensembles

Grande: Gradient-Based Decision Tree Ensembles (arxiv.org)

7 points by PaulHoule 3 years ago | 0 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: No More Adam: Learning Rate Scaling at Initialization Is All You Need

No More Adam: Learning Rate Scaling at Initialization Is All You Need (arxiv.org)

84 points by jinqueeny 1 year ago | 23 comments

Screenshot of arxiv.org: Graph Neural Networks use graphs when they shouldn't

Graph Neural Networks use graphs when they shouldn't (arxiv.org)

112 points by Pseudomanifold 3 years ago | 20 comments

Screenshot of arxiv.org: Magicoder: Source Code Is All You Need

Magicoder: Source Code Is All You Need (arxiv.org)

161 points by tosh 2 years ago | 58 comments