SOURCE-LINKED INTELLIGENCE

A Smoothed Discrepancy Principle for Random Feature Methods and Neural Networks

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

We study data-driven early stopping for spectral regularisation methods in the classical non-parametric regression setting. Building on the discrepancy principle, we propose a multi-scale stopping rule that applies to general kernel estimators and show that, unlike previous approaches, it achieves full adaptivity over all smoothness levels in the well-specified case. A key contribution of our work is an extension based on random feature approximations, which reduces computational cost on large datasets while preserving minimax-optimal statistical guarantees. Our procedure not only selects an o

Read original source ↗ Open in workspace

recordType

paper

region

Global