paper-with-me

홈 › Papers

Risk Phase Transitions in Spiked Regression: Alignment Driven Benign and Catastrophic Overfitting

2025-10-01 · Jiping Li, Rishi Sonthalia arxiv

This paper analyzes the generalization error of minimum-norm interpolating solutions in linear regression using spiked covariance data models. The paper characterizes how varying spike strengths and target-spike alignments can affect risk, especially in overparameterized settings. The study presents an exact expression for the generalization error, leading to a comprehensive classification of benign, tempered, and catastrophic overfitting regimes based on spike strength, the aspect ratio $c=d/n$ (particularly as $c \to \infty$), and target alignment. Notably, in well-specified aligned problems, increasing spike strength can surprisingly induce catastrophic overfitting before achieving benign overfitting. The paper also reveals that target-spike alignment is not always advantageous, identifying specific, sometimes counterintuitive, conditions for its benefit or detriment. Alignment with the spike being detrimental is empirically demonstrated to persist in nonlinear models.

📄 PDF Abstract BibTeX arXiv:2510.01414

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Computational Thresholds in Multi-Modal Learning via the Spiked Matrix-Tensor Model

2025-06-03 · Hugo Tabanelli, Pierre Mergny, Lenka Zdeborova, Florent Krzakala

We study the recovery of multiple high-dimensional signals from two noisy, correlated modalities: a spiked matrix and a spiked tensor sharing a common low-rank structure. This setting generalizes classical spiked matrix …

0-1 phase transitions in sparse spiked matrix estimation

2019-11-12 · Jean Barbier, Nicolas Macris

We consider statistical models of estimation of a rank-one matrix (the spike) corrupted by an additive gaussian noise matrix in the sparse limit. In this limit the underlying hidden vector (that constructs the rank-one m…

Image RestorationObject CountingSemantic SegmentationWord Sense Disambiguation

Missing-Data-Induced Phase Transitions in Spectral PLS for Multimodal Learning

2026-01-29 · Anders Gjølbye, Ida Kargaard, Emma Kargaard, Lina Skerath 외 arxiv

Partial Least Squares (PLS) learns shared structure from paired data via the top singular vectors of the empirical cross-covariance (PLS-SVD), but multimodal datasets often have missing entries in both views. We study PL…

Complex energy landscapes in spiked-tensor and simple glassy models: ruggedness, arrangements of local minima and phase transitions

2018-04-08 · Valentina Ros, Gerard Ben Arous, Giulio Biroli, Chiara Cammarota

We study rough high-dimensional landscapes in which an increasingly stronger preference for a given configuration emerges. Such energy landscapes arise in glass physics and inference. In particular we focus on random Gau…

Signal-Plus-Noise Decomposition of Nonlinear Spiked Random Matrix Models

2024-05-28 · Behrad Moniri, Hamed Hassani

In this paper, we study a nonlinear spiked random matrix model where a nonlinear function is applied element-wise to a noise matrix perturbed by a rank-one signal. We establish a signal-plus-noise decomposition for this …

Community Detection