English
Related papers

Related papers: Worst possible sub-directions in high-dimensional …

200 papers

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 consider the minimization of the number of non-zero coefficients (the $\ell_0$ "norm") of the representation of a data set in terms of a dictionary under a fidelity constraint. (Both the dictionary and the norm defining the constraint…

Optimization and Control · Mathematics 2011-11-07 Francois Malgouyres , Mila Nikolova

We consider the problem of learning high-dimensional Gaussian graphical models. The graphical lasso is one of the most popular methods for estimating Gaussian graphical models. However, it does not achieve the oracle rate of convergence. In…

Machine Learning · Statistics 2017-06-06 Qiang Sun , Kean Ming Tan , Han Liu , Tong Zhang

We consider the problem of estimating the parameters of a Gaussian or binary distribution in such a way that the resulting undirected graphical model is sparse. Our approach is to solve a maximum likelihood problem with an added l_1-norm…

Artificial Intelligence · Computer Science 2007-07-06 Onureena Banerjee , Laurent El Ghaoui , Alexandre d'Aspremont

In many applications, particularly in the natural sciences, the available high-dimensional set of features may contain variables that are not correlated with the response under consideration. Such irrelevant features can, in certain cases,…

Statistics Theory · Mathematics 2025-07-28 Gianluca Finocchio , Tatyana Krivobokova

We study the high-dimensional linear model with noise distribution known up to a scale parameter. With an $\ell_1$-penalty on the regression coefficients, we show that a transformation of the log-likelihood allows for a choice of the tuning…

Statistics Theory · Mathematics 2025-12-23 Sara van de Geer , Sylvain Sardy , Maximę van Cutsem

For statistical modeling wherein the data regime is unfavorable in terms of dimensionality relative to the sample size, finding hidden sparsity in the ground truth can be critical in formulating an accurate statistical model. The so-called…

Optimization and Control · Mathematics 2025-08-04 Matteo Bergamaschi , Andrea Cristofari , Vyacheslav Kungurtsev , Francesco Rinaldi

We consider the optimization of a quadratic objective function whose gradients are only accessible through a stochastic oracle that returns the gradient at any given point plus a zero-mean finite variance random error. We present the first…

Optimization and Control · Mathematics 2016-02-25 Aymeric Dieuleveut , Nicolas Flammarion , Francis Bach

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

Sparse linear regression is a fundamental problem in high-dimensional statistics, but strikingly little is known about how to efficiently solve it without restrictive conditions on the design matrix. We consider the (correlated) random…

Machine Learning · Computer Science 2021-06-18 Jonathan Kelner , Frederic Koehler , Raghu Meka , Dhruv Rohatgi

In a recent paper, it is shown that the LASSO algorithm exhibits "near-ideal behavior," in the following sense: Suppose $y = Az + \eta$ where $A$ satisfies the restricted isometry property (RIP) with a sufficiently small constant, and…

Machine Learning · Statistics 2014-04-22 Mehmet Eren Ahsen , Mathukumalli Vidyasagar

We consider the sparse regression model where the number of parameters $p$ is larger than the sample size $n$. The difficulty when considering high-dimensional problems is to propose estimators achieving a good compromise between…

Statistics Theory · Mathematics 2011-03-15 Pierre Alquier , Karim Lounici

We are concerned here with unrestricted maximum likelihood estimation in a sparse $p_0$ model with covariates for directed networks. The model has a density parameter $\nu$, a $2n$-dimensional node parameter $\bs{\eta}$ and a fixed…

Statistics Theory · Mathematics 2021-06-08 Qiuping Wang

This paper establishes non-asymptotic oracle inequalities for the prediction error and estimation accuracy of the LASSO in stationary vector autoregressive models. These inequalities are used to establish consistency of the LASSO even when…

Statistics Theory · Mathematics 2014-05-16 Anders Bredahl Kock , Laurent A. F. Callot

We analyze the performance of the least absolute shrinkage and selection operator (Lasso) for the linear model when the number of regressors $N$ grows larger keeping the true support size $d$ finite, i.e., the ultra-sparse case. The result…

Disordered Systems and Neural Networks · Physics 2023-02-28 Koki Okajima , Xiangming Meng , Takashi Takahashi , Yoshiyuki Kabashima

In this paper, we investigate the statistical convergence rate of a Bayesian low-rank tensor estimator. Our problem setting is the regression problem where a tensor structure underlying the data is estimated. This problem setting occurs in…

Machine Learning · Statistics 2014-08-14 Taiji Suzuki

The recent work of \cite{CRT,DonohoPol} rigorously proved (in a large dimensional and statistical context) that if the number of equations (measurements in the compressed sensing terminology) in the system is proportional to the length of…

Information Theory · Computer Science 2013-04-02 Mihailo Stojnic

Approximation of high-dimensional functions is a problem in many scientific fields that is only feasible if advantageous structural properties, such as sparsity in a given basis, can be exploited. A relevant tool for analysing sparse…

Numerical Analysis · Mathematics 2023-10-16 Philipp Trunschke , Anthony Nouy , Martin Eigel

We consider a stochastic version of the proximal point algorithm for optimization problems posed on a Hilbert space. A typical application of this is supervised learning. While the method is not new, it has not been extensively analyzed in…

Optimization and Control · Mathematics 2021-09-28 Monika Eisenmann , Tony Stillfjord , Måns Williamson

We consider the high-dimensional linear regression model $Y = X \beta^0 + \epsilon$ with Gaussian noise $\epsilon$ and Gaussian random design $X$. We assume that $\Sigma:= E X^T X / n$ is non-singular and write its inverse as $\Theta :=…

Statistics Theory · Mathematics 2018-08-22 Sara van de Geer