paper-with-me

홈 › Papers

Optimal Algorithms for the Inhomogeneous Spiked Wigner Model

2023-02-13 · NeurIPS 2023 11

In this paper, we study a spiked Wigner problem with an inhomogeneous noise profile. Our aim in this problem is to recover the signal passed through an inhomogeneous low-rank matrix channel. While the information-theoretic performances are well-known, we focus on the algorithmic problem. We derive an approximate message-passing algorithm (AMP) for the inhomogeneous problem and show that its rigorous state evolution coincides with the information-theoretic optimal Bayes fixed-point equations. We identify in particular the existence of a statistical-to-computational gap where known algorithms require a signal-to-noise ratio bigger than the information-theoretic threshold to perform better than random. Finally, from the adapted AMP iteration we deduce a simple and efficient spectral method that can be used to recover the transition for matrices with general variance profiles. This spectral method matches the conjectured optimal computational phase transition.

📄 PDF Abstract BibTeX arXiv:2302.06665

Code (0)

등록된 구현이 없습니다.

Tasks

model

Methods 이 논문이 사용한 방법론

AMP Based on the understanding that the flat local minima of the empirical risk cause the model to generalize better. Adversarial Model Perturbation (AMP) improves generalization via…

Similar Papers 제목 키워드 기반

Spectral Phase Transition and Optimal PCA in Block-Structured Spiked models

2024-03-06 · Pierre Mergny, Justin Ko, Florent Krzakala

We discuss the inhomogeneous spiked Wigner model, a theoretical framework recently introduced to study structured noise in various learning scenarios, through the prism of random matrix theory, with a specific focus on i…

Weak detection in the spiked Wigner model

2018-09-28 · Hye Won Chung, Ji Oon Lee

We consider the weak detection problem in a rank-one spiked Wigner data matrix where the signal-to-noise ratio is small so that reliable detection is impossible. We propose a hypothesis test on the presence of the signal…

model

Asymptotic Normality of Log Likelihood Ratio and Fundamental Limit of the Weak Detection for Spiked Wigner Matrices

2022-03-02 · Hye Won Chung, Jiho Lee, Ji Oon Lee

We consider the problem of detecting the presence of a signal in a rank-one spiked Wigner model. For general non-Gaussian noise, assuming that the signal is drawn from the Rademacher prior, we prove that the log likeliho…

The Algorithmic Phase Transition in Correlated Spiked Models

2025-11-08 · Zhangsong Li arxiv

We study the computational task of detecting and estimating correlated signals in a pair of spiked matrices $$ X=\tfracλ{\sqrt{n}} xu^{\top}+W, \quad Y=\tfracμ{\sqrt{n}} yv^{\top}+Z $$ where the spikes $x,y$ have correla…

Fundamental limits of detection in the spiked Wigner model

2018-06-25 · Ahmed El Alaoui, Florent Krzakala, Michael. I. Jordan

We study the fundamental limits of detecting the presence of an additive rank-one perturbation, or spike, to a Wigner matrix. When the spike comes from a prior that is i.i.d. across coordinates, we prove that the log-lik…