Manifold steering along activation geometry induces behavioral trajectories matching the natural manifold of outputs, while linear steering produces off-manifold unnatural behaviors.
arXiv preprint arXiv:2308.12108 , year =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
For large monomial activation degree, critical points in deep fully-connected networks coincide exactly with subnetwork configurations where neurons are inactive or redundant.
Susceptibilities defined via posterior covariances serve as the Jacobian for mapping data distributions to structural coordinates in Bayesian learning, with pseudo-inverse solving for desired structural changes.
citing papers explorer
-
Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
Manifold steering along activation geometry induces behavioral trajectories matching the natural manifold of outputs, while linear steering produces off-manifold unnatural behaviors.
-
Singular Learning and Occam's Razor in Deep Monomial Networks
For large monomial activation degree, critical points in deep fully-connected networks coincide exactly with subnetwork configurations where neurons are inactive or redundant.
-
Susceptibilities and Patterning: A Primer on Linear Response in Bayesian Learning
Susceptibilities defined via posterior covariances serve as the Jacobian for mapping data distributions to structural coordinates in Bayesian learning, with pseudo-inverse solving for desired structural changes.