English
Related papers

Related papers: The Squared-Error of Generalized LASSO: A Precise …

200 papers

Consider a process satisfying a stochastic differential equation with unknown drift parameter, and suppose that discrete observations are given. It is known that a simple least squares estimator (LSE) can be consistent, but numerically…

Statistics Theory · Mathematics 2017-03-17 Yasutaka Shimizu

In a noiseless linear estimation problem, one aims to reconstruct a vector x* from the knowledge of its linear projections y=Phi x*. There have been many theoretical works concentrating on the case where the matrix Phi is a random i.i.d.…

Machine Learning · Statistics 2020-01-22 Alia Abbara , Antoine Baker , Florent Krzakala , Lenka Zdeborová

In recent years, there is a growing need for processing methods aimed at extracting useful information from large datasets. In many cases the challenge is to discover a low-dimensional structure in the data, often concealed by the existence…

Statistics Theory · Mathematics 2019-06-05 Yariv Aizenbud , Boris Landa , Yoel Shkolnisky

We study a set of regularization methods for high-dimensional linear regression models. These penalized estimators have the square root of the residual sum of squared errors as loss function, and any weakly decomposable norm as penalty…

Statistics Theory · Mathematics 2016-06-28 Benjamin Stucky , Sara van de Geer

In compressed sensing, in order to recover a sparse or nearly sparse vector from possibly noisy measurements, the most popular approach is $\ell_1$-norm minimization. Upper bounds for the $\ell_2$- norm of the error between the true and…

Machine Learning · Statistics 2015-12-31 M. Eren Ahsen , M. Vidyasagar

The objective of this work is to quantify the reconstruction error in sparse inverse problems with measures and stochastic noise, motivated by optimal sensor placement. To be useful in this context, the error quantities must be explicit in…

Numerical Analysis · Mathematics 2024-04-19 Phuoc-Truong Huynh , Konstantin Pieper , Daniel Walter

We consider the problem of sparse normal means estimation in a distributed setting with communication constraints. We assume there are $M$ machines, each holding $d$-dimensional observations of a $K$-sparse vector $\mu$ corrupted by…

Machine Learning · Statistics 2022-02-15 Chen Amiraz , Robert Krauthgamer , Boaz Nadler

We give a new approach to the dictionary learning (also known as "sparse coding") problem of recovering an unknown $n\times m$ matrix $A$ (for $m \geq n$) from examples of the form \[ y = Ax + e, \] where $x$ is a random vector in $\mathbb…

Data Structures and Algorithms · Computer Science 2014-11-11 Boaz Barak , Jonathan A. Kelner , David Steurer

When is optimal estimation linear? It is well known that, when a Gaussian source is contaminated with Gaussian noise, a linear estimator minimizes the mean square estimation error. This paper analyzes, more generally, the conditions for…

Information Theory · Computer Science 2015-03-19 Emrah Akyol , Kumar Viswanatha , Kenneth Rose

We consider a sparse high dimensional regression model where the goal is to recover a $k$-sparse unknown vector $\beta^*$ from $n$ noisy linear observations of the form $Y=X\beta^*+W \in \mathbb{R}^n$ where $X \in \mathbb{R}^{n \times p}$…

Statistics Theory · Mathematics 2019-09-24 David Gamarnik , Ilias Zadik

Signal estimation problems with smoothness and sparsity priors can be naturally modeled as quadratic optimization with $\ell_0$-"norm" constraints. Since such problems are non-convex and hard-to-solve, the standard approach is, instead, to…

Machine Learning · Statistics 2020-10-20 Alper Atamturk , Andres Gomez , Shaoning Han

A fundamental problem in statistics and machine learning is to estimate a function $f$ from possibly noisy observations of its point samples. The goal is to design a numerical algorithm to construct an approximation $\hat f$ to $f$ in a…

Statistics Theory · Mathematics 2025-05-30 Ronald DeVore , Robert D. Nowak , Rahul Parhi , Guergana Petrova , Jonathan W. Siegel

The Lasso is a popular regression method for high-dimensional problems in which the number of parameters $\theta_1,\dots,\theta_N$, is larger than the number $n$ of samples: $N>n$. A useful heuristics relates the statistical properties of…

Statistics Theory · Mathematics 2018-11-06 Léo Miolane , Andrea Montanari

This paper concerns the problem of recovering an unknown but structured signal $x \in R^n$ from $m$ quadratic measurements of the form $y_r=|<a_r,x>|^2$ for $r=1,2,...,m$. We focus on the under-determined setting where the number of…

Machine Learning · Computer Science 2017-02-22 Mahdi Soltanolkotabi

This paper deals with arbitrarily distributed finite-power input signals observed through an additive Gaussian noise channel. It shows a new formula that connects the input-output mutual information and the minimum mean-square error (MMSE)…

Information Theory · Computer Science 2007-07-13 Dongning Guo , Shlomo Shamai , Sergio Verdu

Estimating unknown rotations from noisy measurements is an important step in SfM and other 3D vision tasks. Typically, local optimization methods susceptible to returning suboptimal local minima are used to solve the rotation averaging…

Computer Vision and Pattern Recognition · Computer Science 2019-06-17 Matthew Giamou , Filip Maric , Valentin Peretroukhin , Jonathan Kelly

Compressed sensing typically deals with the estimation of a system input from its noise-corrupted linear measurements, where the number of measurements is smaller than the number of input components. The performance of the estimation…

Information Theory · Computer Science 2016-11-17 Jin Tan , Danielle Carmon , Dror Baron

The estimation of a sparse vector in the linear model is a fundamental problem in signal processing, statistics, and compressive sensing. This paper establishes a lower bound on the mean-squared error, which holds regardless of the…

Information Theory · Computer Science 2013-03-04 Emmanuel J. Candès , Mark A. Davenport

We study the problem of variable selection in convex nonparametric least squares (CNLS). Whereas the least absolute shrinkage and selection operator (Lasso) is a popular technique for least squares, its variable selection performance is…

Methodology · Statistics 2025-10-31 Zhiqiang Liao , Zhaonan Qu

We consider distributed estimation of a Gaussian source in a heterogenous bandwidth constrained sensor network, where the source is corrupted by independent multiplicative and additive observation noises, with incomplete statistical…

Information Theory · Computer Science 2018-05-23 Alireza Sani , Azadeh Vosoughi