For binary classification in the NTK regime, LoRA rank r=1 suffices and is often optimal under cross-entropy loss, reducing the prior sufficient condition from r>=12.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
method 1polarities
use method 1representative citing papers
In the high-dimensional proportional regime, a large gradient step on a two-layer network induces a target-dependent spiked Gaussian covariance on the features, yielding a data-adaptive kernel that amplifies target-aligned eigenvalues and mixes leading eigenfunctions.
A LiDAR-inertial odometry pipeline supplies deterministic feasible sets as protection levels by linking ICP point-cloud noise to pose uncertainty via a closed-form relation and propagating it with an on-manifold ellipsoidal set-membership filter.
citing papers explorer
-
Rethinking the Rank Threshold for LoRA Fine-Tuning
For binary classification in the NTK regime, LoRA rank r=1 suffices and is often optimal under cross-entropy loss, reducing the prior sufficient condition from r>=12.
-
How does feature learning reshape the function space?
In the high-dimensional proportional regime, a large gradient step on a two-layer network induces a target-dependent spiked Gaussian covariance on the features, yielding a data-adaptive kernel that amplifies target-aligned eigenvalues and mixes leading eigenfunctions.
-
Safety-Critical LiDAR-Inertial Odometry with On-Manifold Deterministic Protection Level
A LiDAR-inertial odometry pipeline supplies deterministic feasible sets as protection levels by linking ICP point-cloud noise to pose uncertainty via a closed-form relation and propagating it with an on-manifold ellipsoidal set-membership filter.