Gavia Gray

According to our database¹, Gavia Gray authored at least 3 papers between 2024 and 2025.

Collaborative distances:

Dijkstra number² of five.
Erdős number³ of five.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Links

On csauthors.net:

Bibliography

2025

Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training.

[BibT_eX]

[DOI]

CoRR, May, 2025

Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Gavia Gray

Timeline

Legend:

Links

On csauthors.net:

Bibliography

Loading...