中文
相关论文

相关论文: Mismatched estimation of non-symmetric rank-one ma…

200 篇论文

We consider the problem of estimating a rank-1 signal corrupted by structured rotationally invariant noise, and address the following question: how well do inference algorithms perform when the noise statistics is unknown and hence Gaussian…

信息论 · 计算机科学 2022-05-23 Jean Barbier , TianQi Hou , Marco Mondelli , Manuel Sáenz

Consider the problem of estimating a low-rank matrix when its entries are perturbed by Gaussian noise. If the empirical distribution of the entries of the spikes is known, optimal estimators that exploit this knowledge can substantially…

统计理论 · 数学 2019-08-08 Andrea Montanari , Ramji Venkataramanan

We consider the estimation of an n-dimensional vector s from the noisy element-wise measurements of $\mathbf{s}\mathbf{s}^T$, a generic problem that arises in statistics and machine learning. We study a mismatched Bayesian inference…

信息论 · 计算机科学 2021-09-14 Farzad Pourkamali , Nicolas Macris

We investigate the performance of a Bayesian statistician tasked with recovering a rank-\(k\) signal matrix \(\bS \bS^{\top} \in \mathbb{R}^{n \times n}\), corrupted by element-wise additive Gaussian noise. This problem lies at the core of…

信息论 · 计算机科学 2025-07-17 Panpan Niu , Yuhao Liu , Teng Fu , Jie Fan , Chaowen Deng , Zhongyi Huang

How do statistical dependencies in measurement noise influence high-dimensional inference? To answer this, we study the paradigmatic spiked matrix model of principal components analysis (PCA), where a rank-one matrix is corrupted by…

信息论 · 计算机科学 2023-06-05 Jean Barbier , Francesco Camilli , Marco Mondelli , Manuel Saenz

We consider the problem of signal estimation in generalized linear models defined via rotationally invariant design matrices. Since these matrices can have an arbitrary spectral distribution, this model is well suited for capturing complex…

机器学习 · 统计学 2022-06-10 Ramji Venkataramanan , Kevin Kögler , Marco Mondelli

We consider the task of estimating a low-rank matrix from non-linear and noisy observations. We prove a strong universality result showing that Bayes-optimal performances are characterized by an equivalent Gaussian model with an effective…

机器学习 · 统计学 2024-03-08 Pierre Mergny , Justin Ko , Florent Krzakala , Lenka Zdeborová

We study the problem of estimating a rank one signal matrix from an observed matrix generated by corrupting the signal with additive rotationally invariant noise. We develop a new class of approximate message-passing algorithms for this…

统计理论 · 数学 2025-09-09 Rishabh Dudeja , Songbin Liu , Junjie Ma

We study a class of Approximate Message Passing (AMP) algorithms for symmetric and rectangular spiked random matrix models with orthogonally invariant noise. The AMP iterates have fixed dimension $K \geq 1$, a multivariate non-linearity is…

统计理论 · 数学 2024-06-14 Xinyi Zhong , Tianhao Wang , Zhou Fan

This paper is concerned with the problem of reconstructing an unknown rank-one matrix with prior structural information from noisy observations. While computing the Bayes-optimal estimator seems intractable in general due to its nonconvex…

统计理论 · 数学 2023-02-08 Gen Li , Wei Fan , Yuting Wei

We consider a prototypical problem of Bayesian inference for a structured spiked model: a low-rank signal is corrupted by additive noise. While both information-theoretic and algorithmic limits are well understood when the noise is a…

信息论 · 计算机科学 2024-07-09 Jean Barbier , Francesco Camilli , Marco Mondelli , Yizhou Xu

We study the problem of estimating a rank-$1$ signal in the presence of rotationally invariant noise-a class of perturbations more general than Gaussian noise. Principal Component Analysis (PCA) provides a natural estimator, and sharp…

机器学习 · 统计学 2021-10-15 Marco Mondelli , Ramji Venkataramanan

Nonlinear function estimation is core to modern machine learning applications. In this paper, to perform nonlinear function estimation, we reduce a nonlinear inverse problem to a linear one using a polynomial kernel expansion. These kernels…

信息论 · 计算机科学 2019-10-02 Hangjin Liu , You , Zhou , Ahmad Beirami , Dror Baron

Approximate Message Passing (AMP) algorithms have seen widespread use across a variety of applications. However, the precise forms for their Onsager corrections and state evolutions depend on properties of the underlying random matrix…

概率论 · 数学 2021-08-16 Zhou Fan

Approximate message passing algorithm enjoyed considerable attention in the last decade. In this paper we introduce a variant of the AMP algorithm that takes into account glassy nature of the system under consideration. We coin this…

无序系统与神经网络 · 物理学 2019-02-07 Fabrizio Antenucci , Florent Krzakala , Pierfrancesco Urbani , Lenka Zdeborová

When recovering a sparse signal from noisy compressive linear measurements, the distribution of the signal's non-zero coefficients can have a profound effect on recovery mean-squared error (MSE). If this distribution was apriori known, then…

信息论 · 计算机科学 2015-06-05 Jeremy P. Vila , Philip Schniter

In a recent article (Proc. Natl. Acad. Sci., 110(36), 14557-14562), El Karoui et al. study the distribution of robust regression estimators in the regime in which the number of parameters p is of the same order as the number of samples n.…

统计理论 · 数学 2013-11-18 David Donoho , Andrea Montanari

We propose an orthogonal approximate message passing (OAMP) algorithm for signal estimation in the rectangular spiked matrix model with general rotationally invariant (RI) noise. We establish a rigorous state evolution that exactly…

统计理论 · 数学 2026-02-04 Haohua Chen , Songbin Liu , Junjie Ma

We consider the problem of estimating a rank-one matrix in Gaussian noise under a probabilistic model for the left and right factors of the matrix. The probabilistic model can impose constraints on the factors including sparsity and…

信息论 · 计算机科学 2015-09-16 Alyson K. Fletcher , Sundeep Rangan

Approximate message passing (AMP) is a low-cost iterative parameter-estimation technique for certain high-dimensional linear systems with non-Gaussian distributions. However, AMP only applies to independent identically distributed (IID)…

信息论 · 计算机科学 2021-06-07 Lei Liu , Shunqi Huang , Brian M. Kurkoski
‹ 上一页 1 2 3 10 下一页 ›