A data-parameter correspondence unifies data-centric and parameter-centric LLM optimizations as dual geometric operations on the statistical manifold via Fisher-Rao metric and Legendre duality.
Robust large margin deep neural networks,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
Towards a Data-Parameter Correspondence for LLMs: A Preliminary Discussion
A data-parameter correspondence unifies data-centric and parameter-centric LLM optimizations as dual geometric operations on the statistical manifold via Fisher-Rao metric and Legendre duality.
- Jacobian-Velocity Bounds for Deployment Risk Under Covariate Drift