Derives geodesic ridge regularization and Riemannian Gibbs Process prior for feature-learning wide neural networks, generalizing kernel-regime results via function-space axiomatization.
Ridge regression: Biased estimation for nonorthogonal problems.Technometrics, 12(1):55–67
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
TextReg mitigates prompt distributional overfitting via regularized text-space optimization, reporting up to +16.5% OOD accuracy gains over prior methods on reasoning benchmarks.
Brain data is worth a variable number of task samples depending on task-brain alignment, noise levels, and latent dimension, with conditions under which it also improves robustness to test distribution shift.
ConformaDecompose decomposes conformal prediction uncertainty by progressively localizing calibration sets, revealing reducible epistemic components that align with model limitations across tasks.
citing papers explorer
-
Canonical Regularisation of Wide Feature-Learning Neural Networks
Derives geodesic ridge regularization and Riemannian Gibbs Process prior for feature-learning wide neural networks, generalizing kernel-regime results via function-space axiomatization.
-
TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization
TextReg mitigates prompt distributional overfitting via regularized text-space optimization, reporting up to +16.5% OOD accuracy gains over prior methods on reasoning benchmarks.
-
How Much is Brain Data Worth for Machine Learning?
Brain data is worth a variable number of task samples depending on task-brain alignment, noise levels, and latent dimension, with conditions under which it also improves robustness to test distribution shift.
-
ConformaDecompose: Explaining Uncertainty via Calibration Localization
ConformaDecompose decomposes conformal prediction uncertainty by progressively localizing calibration sets, revealing reducible epistemic components that align with model limitations across tasks.