Preprint / scholarly article
A Model-Agnostic, Performance-Pushforward Theory of Scaling Laws
- Published
- DOI
- 10.5281/zenodo.17520859
Abstract
The central idea is to view performance as the pushforward of an EVI λ gradient flow under a Lipschitz evaluation map, while scale is measured by the geometry of preimages of performance targets.
Keywords
- large language models
- AI
- machine learning
- optimization
- information theory
- numerical analysis
- computer science
- scaling laws
- gradient flows
- ambrosio-gigli-savaré
- evi