AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Optimal Pruning for Neural Architectures using Fisher Information Distances

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

A new scheme for parameter pruning is introduced, derived from the differential-geometric distance in model space. Pruning a parameter sets its value to zero, representing a displacement of the model to the hypersurface on which that parameter vanishes. The minimal distance from the unpruned model to this hypersurface is naturally computed via the geodesic distance in the model space as determined by the Fisher information metric. This distance determines the true change in the model, and its performance, under pruning. By analysing progressively more faithful approximations of this geodesic d

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-20T09:41:04.278Z. This is not the publication date.