English
Related papers

Related papers: Sparser Johnson-Lindenstrauss Transforms

200 papers

For the Gaussian sequence model, we obtain non-asymptotic minimax rates of estimation of the linear, quadratic and the L2-norm functionals on classes of sparse vectors and construct optimal estimators that attain these rates. The main…

Statistics Theory · Mathematics 2015-02-04 Olivier Collier , Laëtitia Comminges , Alexandre B. Tsybakov

In this paper we study the robustness properties of dimensionality reduction with Gaussian random matrices having arbitrarily erased rows. We first study the robustness property against erasure for the almost norm preservation property of…

Information Theory · Computer Science 2015-01-09 Bin Han , Zhiqiang Xu

The performance of machine learning and pattern recognition algorithms generally depends on data representation. That is why, much of the current effort in performing machine learning algorithms goes into the design of preprocessing…

Machine Learning · Computer Science 2025-10-28 Fadi Dornaika , Ahmad Khoder , Abdelmalik Moujahid , Wassim Khoder

We study the $\ell_p$ regression problem, which requires finding $\mathbf{x}\in\mathbb R^{d}$ that minimizes $\|\mathbf{A}\mathbf{x}-\mathbf{b}\|_p$ for a matrix $\mathbf{A}\in\mathbb R^{n \times d}$ and response vector…

Data Structures and Algorithms · Computer Science 2022-03-16 Raphael A. Meyer , Cameron Musco , Christopher Musco , David P. Woodruff , Samson Zhou

This paper introduces the Reed Muller Sieve, a deterministic measurement matrix for compressed sensing. The columns of this matrix are obtained by exponentiating codewords in the quaternary second order Reed Muller code of length $N$. For…

Information Theory · Computer Science 2010-04-20 Robert Calderbank , Stephen Howard , Sina Jafarpour

Sparsity plays a central role in recent developments in signal processing, linear algebra, statistics, optimization, and other fields. In these developments, sparsity is promoted through the addition of an $L^1$ norm (or related quantity)…

Analysis of PDEs · Mathematics 2014-08-04 Russel E. Caflisch , Stanley J. Osher , Hayden Schaeffer , Giang Tran

Given the observation of a high-dimensional Ornstein-Uhlenbeck (OU) process in continuous time, we proceed to the inference of the drift parameter under a row-sparsity assumption. Towards that aim, we consider the negative log-likelihood of…

Machine Learning · Statistics 2017-07-12 Stéphane Gaïffas , Gustaw Matulewicz

The article concerns compressed sensing methods in the quaternion algebra. We prove that it is possible to uniquely reconstruct - by $\ell_1$-norm minimization - a sparse quaternion signal from a limited number of its linear measurements,…

Functional Analysis · Mathematics 2017-05-23 Agnieszka Badeńska , Łukasz Błaszczyk

We consider the least-square linear regression problem with regularization by the $\ell^1$-norm, a problem usually referred to as the Lasso. In this paper, we first present a detailed asymptotic analysis of model consistency of the Lasso in…

Machine Learning · Computer Science 2009-01-22 Francis Bach

Designing computational experiments involving $\ell_1$ minimization with linear constraints in a finite-dimensional, real-valued space for receiving a sparse solution with a precise number $k$ of nonzero entries is, in general, difficult.…

Optimization and Control · Mathematics 2013-09-11 Christian Kruschel , Dirk A. Lorenz

We present a detailed analysis of the unconstrained $\ell_1$-weighted LASSO method for recovery of sparse data from its observation by randomly generated matrices, satisfying the Restricted Isometry Property (RIP) with constant $\delta<1$,…

Information Theory · Computer Science 2022-03-16 Simon Foucart , Eitan Tadmor , Ming Zhong

We investigate the sparse recovery problem of reconstructing a high-dimensional non-negative sparse vector from lower dimensional linear measurements. While much work has focused on dense measurement matrices, sparse measurement schemes are…

Information Theory · Computer Science 2009-02-25 M. Amin Khajehnejad , Alexandros G. Dimakis , Weiyu Xu , Babak Hassibi

It was recently established that for convex optimization problems with sparse optimal solutions (be it entry-wise sparsity or matrix rank-wise sparsity) it is possible to design first-order methods with linear convergence rates that depend…

Optimization and Control · Mathematics 2026-03-20 Dan Garber

We consider the problem of linear regression where the $\ell_2^n$ norm loss (i.e., the usual least squares loss) is replaced by the $\ell_p^n$ norm. We show how to solve such problems up to machine precision in $O^*(n^{|1/2 - 1/p|})$…

Optimization and Control · Mathematics 2018-06-26 Sébastien Bubeck , Michael B. Cohen , Yin Tat Lee , Yuanzhi Li

We consider a minimization problem whose objective function is the sum of a fidelity term, not necessarily convex, and a regularization term defined by a positive regularization parameter $\lambda$ multiple of the $\ell_0$ norm composed…

Optimization and Control · Mathematics 2021-11-17 Yuesheng Xu

We propose computationally efficient encoders and decoders for lossy compression using a Sparse Regression Code. The codebook is defined by a design matrix and codewords are structured linear combinations of columns of this matrix. The…

Information Theory · Computer Science 2014-05-20 Ramji Venkataramanan , Tuhin Sarkar , Sekhar Tatikonda

This paper investigates the effect of the design matrix on the ability (or inability) to estimate a sparse parameter in linear regression. More specifically, we characterize the optimal rate of estimation when the smallest singular value of…

Statistics Theory · Mathematics 2024-02-02 Reese Pathak , Cong Ma

Estimation of the precision matrix (or inverse covariance matrix) is of great importance in statistical data analysis and machine learning. However, as the number of parameters scales quadratically with the dimension $p$, computation…

Computation · Statistics 2022-11-02 Qian LI , Binyan Jiang , Defeng Sun

The significant progress in constructing graph spanners that are sparse (small number of edges) or light (low total weight) has skipped spanners that are everywhere-sparse (small maximum degree). This disparity is in line with other network…

Data Structures and Algorithms · Computer Science 2012-05-02 Eden Chlamtac , Michael Dinitz , Robert Krauthgamer

A recurring theme in attempts to break the curse of dimensionality in the numerical approximations of solutions to high-dimensional partial differential equations (PDEs) is to employ some form of sparse tensor approximation. Unfortunately,…

Numerical Analysis · Mathematics 2014-07-24 Wolfgang Dahmen , Ronald DeVore , Lars Grasedyck , Endre Süli