中文
相关论文

相关论文: Minimax risk of matrix denoising by singular value…

200 篇论文

Recovering nonlinearly degraded signal in the presence of noise is a challenging problem. In this work, this problem is tackled by minimizing the sum of a non convex least-squares fit criterion and a penalty term. We assume that the…

信号处理 · 电气工程与系统科学 2019-02-27 Marc Castella , Jean-Christophe Pesquet , Arthur Marmin

Across many disciplines from neuroscience and genomics to machine learning, atmospheric science and finance, the problems of denoising large data matrices to recover signals obscured by noise, and of estimating the structure of these…

数据分析、统计与概率 · 物理学 2023-12-06 Itamar D. Landau , Gabriel C. Mel , Surya Ganguli

We study the problem of designing minimax procedures in linear regression under the quantile risk. We start by considering the realizable setting with independent Gaussian noise, where for any given noise level and distribution of inputs,…

统计理论 · 数学 2024-06-19 Ayoub El Hanchi , Chris J. Maddison , Murat A. Erdogdu

We perturb a real matrix $A$ of full column rank, and derive lower bounds for the smallest singular values of the perturbed matrix, in terms of normwise absolute perturbations. Our bounds, which extend existing lower-order expressions,…

数值分析 · 数学 2024-02-22 Christos Boutsikas , Petros Drineas , Ilse C. F. Ipsen

We study the problem of estimating a large, low-rank matrix corrupted by additive noise of unknown covariance, assuming one has access to additional side information in the form of noise-only measurements. We study the Whiten-Shrink-reColor…

统计理论 · 数学 2023-07-18 Matan Gavish , William Leeb , Elad Romanov

Matrix completion has been well studied under the uniform sampling model and the trace-norm regularized methods perform well both theoretically and numerically in such a setting. However, the uniform sampling model is unrealistic for a…

机器学习 · 计算机科学 2017-05-01 T. Tony Cai , Wen-Xin Zhou

We analyze a class of estimators based on convex relaxation for solving high-dimensional matrix decomposition problems. The observations are noisy realizations of a linear transformation $\mathfrak{X}$ of the sum of an approximately) low…

机器学习 · 统计学 2012-08-09 Alekh Agarwal , Sahand N. Negahban , Martin J. Wainwright

We show that solutions to the popular convex matrix LASSO problem (nuclear-norm--penalized linear least-squares) have low rank under similar assumptions as required by classical low-rank matrix sensing error bounds. Although the purpose of…

最优化与控制 · 数学 2026-04-16 Andrew D. McRae

The problem of low-rank matrix completion with heterogeneous and sub-exponential (as opposed to homogeneous and Gaussian) noise is particularly relevant to a number of applications in modern commerce. Examples include panel sales data and…

机器学习 · 统计学 2021-10-26 Vivek F. Farias , Andrew A. Li , Tianyi Peng

Higher-order tensors arise frequently in applications such as neuroimaging, recommendation system, social network analysis, and psychological studies. We consider the problem of low-rank tensor estimation from possibly incomplete,…

机器学习 · 统计学 2020-12-15 Chanwoo Lee , Miaoyan Wang

The inference of a large symmetric signal-matrix $\mathbf{S} \in \mathbb{R}^{N\times N}$ corrupted by additive Gaussian noise, is considered for two regimes of growth of the rank $M$ as a function of $N$. For sub-linear ranks…

信息论 · 计算机科学 2024-07-16 Farzad Pourkamali , Jean Barbier , Nicolas Macris

We study the completion of approximately low rank matrices with entries missing not at random (MNAR). In the context of typical large-dimensional statistical settings, we establish a framework for the performance analysis of the nuclear…

信息论 · 计算机科学 2024-01-02 Agostino Capponi , Mihailo Stojnic

We address the problem of estimating a sparse low-rank matrix from its noisy observation. We propose an objective function consisting of a data-fidelity term and two parameterized non-convex penalty functions. Further, we show how to set…

最优化与控制 · 数学 2017-04-13 Ankit Parekh , Ivan W. Selesnick

We observe $(X_i,Y_i)_{i=1}^n$ where the $Y_i$'s are real valued outputs and the $X_i$'s are $m\times T$ matrices. We observe a new entry $X$ and we want to predict the output $Y$ associated with it. We focus on the high-dimensional…

统计理论 · 数学 2010-09-01 Stéphane Gaïffas , Guillaume Lecué

We propose a data-driven algorithm for the maximum a posteriori (MAP) estimation of stochastic processes from noisy observations. The primary statistical properties of the sought signal is specified by the penalty function (i.e., negative…

机器学习 · 计算机科学 2018-02-14 Ha Q. Nguyen , Emrah Bostan , Michael Unser

This paper studies fine-grained singular subspace estimation in the matrix denoising model where a deterministic low-rank signal matrix is additively perturbed by a stochastic matrix of Gaussian noise. We establish that the maximum…

统计理论 · 数学 2025-11-27 Junhyung Chang , Joshua Cape

To recover a low rank structure from a noisy matrix, truncated singular value decomposition has been extensively used and studied. Recent studies suggested that the signal can be better estimated by shrinking the singular values. We pursue…

统计方法学 · 统计学 2014-11-25 Julie Josse , Sylvain Sardy

This work studies an experimental design problem where {the values of a predictor variable, denoted by $x$}, are to be determined with the goal of estimating a function $m(x)$, which is observed with noise. A linear model is fitted to…

统计理论 · 数学 2023-05-03 David Azriel

In many real-world classification problems, the labels of training examples are randomly corrupted. Most previous theoretical work on classification with label noise assumes that the two classes are separable, that the label noise is…

机器学习 · 统计学 2016-08-08 Gilles Blanchard , Marek Flaska , Gregory Handy , Sara Pozzi , Clayton Scott

The Nystr\"om method is a popular choice for finding a low-rank approximation to a symmetric positive semi-definite matrix. The method can fail when applied to symmetric indefinite matrices, for which the error can be unboundedly large. In…

数值分析 · 数学 2023-10-10 Taejun Park , Yuji Nakatsukasa