Study measures how neural representations form during training
Path tortuosity, not endpoint displacement, predicted later drift and sensitivity to parameter perturbations.
Stories per day · 30 days
3 stories, newest first · one card per story
Stories tagged #information-geometry
The information geometry of large language models is shared, learned, and controllable
Fisher-Rao output geometry is shared across LLM architectures and enables minimum-disturbance interventions that transfer across prompts for steering and editing.
A Generalization of Amari's Bayesian Duality
Paper generalizes Amari's Bayesian duality by connecting it to a convex duality of Bayes' rule.