SOURCE-LINKED INTELLIGENCE

Unified Response Geometry for Structured Pruning

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Structured pruning is commonly formulated as ranking individual channels, although channel responses can be complementary or cancel through downstream mixing. Motivated by these response interactions, we formulate pruning as the selection of a subset with large joint response capacity, followed by a separate functional realization step. Our unified response geometry maps each candidate set to \(M(D,R)=D^{1/2}RD^{1/2}\) and uses its determinant together with Schur-greedy residuals to select non-redundant coordinates. The same construction yields two information-conditioned instances: an unlabel

Read original source ↗ Open in workspace

recordType

paper

region

Global