English
Related papers

Related papers: Sharp thresholds for high-dimensional and noisy re…

200 papers

It is well known that $\ell_1$ minimization can be used to recover sufficiently sparse unknown signals from compressed linear measurements. In fact, exact thresholds on the sparsity, as a function of the ratio between the system dimensions,…

Information Theory · Computer Science 2011-11-08 M. Amin Khajehnejad , Weiyu Xu , A. Salman Avestimehr , Babak Hassibi

We analyze a practical algorithm for sparse PCA on incomplete and noisy data under a general non-random sampling scheme. The algorithm is based on a semidefinite relaxation of the $\ell_1$-regularized PCA problem. We provide theoretical…

Machine Learning · Statistics 2023-02-06 Hanbyul Lee , Qifan Song , Jean Honorio

A noisy underdetermined system of linear equations is considered in which a sparse vector (a vector with a few nonzero elements) is subject to measurement. The measurement matrix elements are drawn from a Gaussian distribution. We study the…

Information Theory · Computer Science 2014-06-26 Behrooz Kamary Aliabadi , Silèye Ba

Orthogonal Matching pursuit (OMP) is a popular algorithm to estimate an unknown sparse vector from multiple linear measurements of it. Assuming exact sparsity and that the measurements are corrupted by additive Gaussian noise, the success…

Statistics Theory · Mathematics 2020-08-07 Chen Amiraz , Robert Krauthgamer , Boaz Nadler

Sparsity promoting norms are frequently used in high dimensional regression. A limitation of such Lasso-type estimators is that the optimal regularization parameter depends on the unknown noise level. Estimators such as the concomitant…

Machine Learning · Statistics 2020-09-04 Quentin Bertrand , Mathurin Massias , Alexandre Gramfort , Joseph Salmon

We consider the problem of exact support recovery of sparse signals via noisy measurements. The main focus is the sufficient and necessary conditions on the number of measurements for support recovery to be reliable. By drawing an analogy…

Information Theory · Computer Science 2010-03-04 Yuzhe Jin , Young-Han Kim , Bhaskar D. Rao

We consider the problem of recovering sparse vectors from underdetermined linear measurements via $\ell_p$-constrained basis pursuit. Previous analyses of this problem based on generalized restricted isometry properties have suggested that…

Information Theory · Computer Science 2015-04-21 Sjoerd Dirksen , Guillaume Lecué , Holger Rauhut

We consider the Orthogonal Least-Squares (OLS) algorithm for the recovery of a $m$-dimensional $k$-sparse signal from a low number of noisy linear measurements. The Exact Recovery Condition (ERC) in bounded noisy scenario is established for…

Machine Learning · Statistics 2016-08-09 Abolfazl Hashemi , Haris Vikalo

In genetics it is often of interest to discover single nucleotide polymorphisms (SNPs) that are directly related to a disease, rather than just being associated with it. Few methods exist, however, addressing this so-called `true sparsity…

Applications · Statistics 2011-07-28 Matthew Sperrin , Thomas Jaki

Efficient recovery of a low-dimensional structure from high-dimensional data has been pursued in various settings including wavelet denoising, generalized linear models and low-rank matrix estimation. By thresholding some parameters to…

Methodology · Statistics 2017-08-14 Caroline Giacobino , Sylvain Sardy , Jairo Diaz-Rodriguez , Nick Hengartner

Estimating high-dimensional precision matrices is a fundamental problem in modern statistics, with the graphical lasso and its $\ell_1$-penalty being a standard approach for recovering sparsity patterns. However, many statistical models,…

Statistics Theory · Mathematics 2025-06-19 Piotr Graczyk , Bartosz Kołodziejek , Hideto Nakashima , Maciej Wilczyński

This paper investigates theoretical properties of subsampling and hashing as tools for approximate Euclidean norm-preserving embeddings for vectors with (unknown) additive Gaussian noises. Such embeddings are sometimes called…

Data Structures and Algorithms · Computer Science 2022-09-05 Zhen Shao

High-dimensional data often lie in low-dimensional subspaces corresponding to different classes they belong to. Finding sparse representations of data points in a dictionary built using the collection of data helps to uncover…

Machine Learning · Statistics 2016-02-16 Ehsan Elhamifar , Mahdi Soltanolkotabi , Shankar Sastry

We propose a pivotal method for estimating high-dimensional sparse linear regression models, where the overall number of regressors $p$ is large, possibly much larger than $n$, but only $s$ regressors are significant. The method is a…

Methodology · Statistics 2015-03-17 Alexandre Belloni , Victor Chernozhukov , Lie Wang

We present a sparse analogue to stochastic gradient descent that is guaranteed to perform well under similar conditions to the lasso. In the linear regression setup with irrepresentable noise features, our algorithm recovers the support set…

Statistics Theory · Mathematics 2014-12-16 Jacob Steinhardt , Stefan Wager , Percy Liang

In high dimension, it is customary to consider Lasso-type estimators to enforce sparsity. For standard Lasso theory to hold, the regularization parameter should be proportional to the noise level, yet the latter is generally unknown in…

Machine Learning · Statistics 2017-10-19 Mathurin Massias , Olivier Fercoq , Alexandre Gramfort , Joseph Salmon

We study the problem of sparse tensor principal component analysis: given a tensor $\pmb Y = \pmb W + \lambda x^{\otimes p}$ with $\pmb W \in \otimes^p\mathbb{R}^n$ having i.i.d. Gaussian entries, the goal is to recover the $k$-sparse unit…

Machine Learning · Computer Science 2021-11-03 Davin Choo , Tommaso d'Orsi

We study the recovery of sparse vectors from subsampled random convolutions via $\ell_1$-minimization. We consider the setup in which both the subsampling locations as well as the generating vector are chosen at random. For a subgaussian…

Information Theory · Computer Science 2018-03-28 Shahar Mendelson , Holger Rauhut , Rachel Ward

This paper is concerned with high-dimensional panel data models where the number of regressors can be much larger than the sample size. Under the assumption that the true parameter vector is sparse we propose a panel-Lasso estimator and…

Statistics Theory · Mathematics 2014-02-14 Anders Bredahl Kock

Vector valued data appearing in concrete applications often possess sparse expansions with respect to a preassigned frame for each vector component individually. Additionally, different components may also exhibit common sparsity patterns.…

Numerical Analysis · Mathematics 2007-05-23 Massimo Fornasier , Holger Rauhut