✳flâneur — a map of the web's best reading
Scaling Laws Literature Review
epochai.org · 1,921 words · saved by 1 readers
I have collected a database of scaling laws for different tasks and architectures, and reviewed dozens of papers in the scaling law literature.
Scaling laws literature review | Epoch AI Common shape of a scaling law, taken from Hestness et al. (2017) Executive summary Scaling laws are predictable relations between the scale of a mode and performance or other useful properties. I have collected a database of scaling laws for different tasks and architectures, and reviewed dozens of papers in the scaling law literature. My main takeaways are: Functional forms : a basic power law can effectively model the scaling behavior in the power-law region but not the transitions to the other two regions. For this, either the M4 estimator or the BN
Explore this link on the map →related reading
- The Scaling Hypothesis · Gwern.netgwern.net
- Scaling Laws, Carefully | Lil'Loglilianweng.github.io
- On neural scaling and the quanta hypothesisericjmichaud.com
- [2001.08361] Scaling Laws for Neural Language Modelsarxiv.org
- [2411.12925] Loss-to-Loss Prediction: Scaling Laws for All Datasetsarxiv.org
- Demystify Transformers: A Guide to Scaling Laws | by Yu-Cheng Tsai | Sage Ai | Mediummedium.com
- How To Scale Your Modeljax-ml.github.io
- New Scaling Laws for Large Language Models — LessWronglesswrong.com
- [2405.10938] Observational Scaling Laws and the Predictability of Language Model Performancearxiv.org
- [2602.05970] Inverse Depth Scaling From Most Layers Being Similararxiv.org
- The Little Book of Deep Learningfleuret.org
- RL Scaling Laws for LLMs - by Cameron R. Wolfe, Ph.D.cameronrwolfe.substack.com