EPS
← All batches·2605.15240

On Kernel Eigen-alignments of KRR: Reconstruction and Generalization

topic: current_projecttop score: 100released: 2026-05-18first surfaced: 2026-05-18arXivPDFlinked_to_results2026-05-18

Authors: Yang Liu, Ernest Fokoue, Richard Lange et al.

arXiv · PDF

Summary

arXiv:2605. 15240v1 Announce Type: new Abstract: This paper investigates the critical role of eigenalignments between the kernel matrix and learning targets in achieving robust generalization in learning problems.

Relevance

Read next because On Kernel Eigen-alignments of KRR: Reconstruction and Generalization overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: strong, rect, under, alignment, rate, compare. Source: arxiv stat.ML (Machine Learning).

Abstract

arXiv:2605.15240v1 Announce Type: new Abstract: This paper investigates the critical role of eigenalignments between the kernel matrix and learning targets in achieving robust generalization in learning problems. We establish a direct connection between generalization performance in kernel methods and the estimation of eigenvectors and eigenvalues of matrices, offering a more intuitive understanding compared to prior work with minimal assumptions. We also show that, since the prediction task in KRR is essentially the weighted sum of eigenvectors/singular vectors, by analyzing how much error can be caused by perturbations to the kernel matrix, we can then derive a bound on this generalization error using the estimation stability of matrix eigenvalues and eigenvectors. Compared with previous work, our analysis concentrates on finite-sample settings and on the generalization error arising from having a suboptimal finite training set. Our findings reveal that in kernel methods, as long as the kernel is of high rank, the near-zero reconstruction error can be trivially obtained, implying that the reconstruction error will have limited predictive power for generalization. Finally, we establish a generalization bound from an eigenvalues/eigenvectors estimation perspective, showing that strong generalization requires increasing eigenvector alignment, eigenvalue magnitude, or gaps between consecutive eigenvalues.