arXiv Machine Learning
Compact and Infinite-Order Error Analysis for Null-Space SVD Estimation
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Sep 22
On Kernel Eigen-alignments of KRR: Reconstruction and Generalization
arXiv:2605.15240v2 Announce Type: replace-cross Abstract: This paper investigates the critical role of eigenalignments between the kernel matrix and learning targets in achieving robust generalizatio...
arXiv Machine Learning
Aug 20
Inference and Uncertainty Quantification for Streaming $r$-PCA
The paper tackles two key gaps in streaming PCA using Oja's algorithm: it establishes sharp operator‑norm convergence for general‑rank subspaces under sub‑Gaussian data, and it provides distributional inference for the resulting subspace estimator. The authors remove non‑vanishing remainder terms from existing analyses, achieving rates that match minimax bounds in both dense‑tail and sparse‑tail regimes. They further develop a linearization of Oja’s iterates, enabling high‑dimensional Gaussian approximations and an online multiplier bootstrap for practical inference.
arXiv Machine Learning
Jun 16
Stochastic trace estimation with tensor train random vectors
arXiv:2606. 15679v1 Announce Type: cross Abstract: Stochastic trace estimation is a standard tool for approximating the trace of a large-scale matrix available only through matrix-vector products.
arXiv Machine Learning
Aug 18
Spectral Rank Certification for Foundation Model Adapters
arXiv:2608. 15351v1 Announce Type: new Abstract: Nominal LoRA rank is a design parameter; calibrated spectral evidence is a separate inferential quantity.
arXiv Machine Learning
Jul 31
Tight Sample Complexity for Low-Rank Adaptation: Matching Bounds and Rank Selection
arXiv:2607. 27680v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has become the standard mechanism for fine-tuning large pretrained models, yet its statistical properties remain only partially understood.
Hugging Face Trending Papers
Sep 29
Interpretable intrinsic dimension estimation through componentwise calibration of distance and angle
DANCo (Dimensionality from Angle and Norm Concentration) jointly calibrates nearest-neighbor distance and angular statistics and consistently reaches state-of-the-art accuracy on clean intrinsic-dimen...