Preprint / scholarly article
Compute-Optimal AI via Image--EVI, Interior Bures--HK Control, and Fractal Dendritic Approximation (DIR)
- Published
- DOI
- 10.5281/zenodo.17576546
Abstract
Here alpha and beta are the empirical scaling exponents for parameters and tokens, is a robust image Lipschitz proxy, and (eta, rho) encode slack from acceptance tests.
Keywords
- AI
- large language models
- geometry
- information theory
- compute reduction
- scaling laws
- entropy-transport
- hellinger-kantorovich