English
Related papers

Related papers: A new perspective on least squares under convex co…

200 papers

This paper considers the penalized least squares estimator with arbitrary convex penalty. When the observation noise is Gaussian, we show that the prediction error is a subgaussian random variable concentrated around its median. We apply…

Statistics Theory · Mathematics 2016-09-22 Pierre C. Bellec , Alexandre B. Tsybakov

There is growing interest in improving our algorithmic understanding of fundamental statistical problems such as mean estimation, driven by the goal of understanding the limits of what we can extract from valuable data. The state of the art…

Statistics Theory · Mathematics 2023-11-22 Trung Dang , Jasper C. H. Lee , Maoyuan Song , Paul Valiant

In covariance matrix estimation, one of the challenges lies in finding a suitable model and an efficient estimation method. Two commonly used modelling approaches in the literature involve imposing linear restrictions on the covariance…

Statistics Theory · Mathematics 2024-05-09 Piotr Zwiernik

Modern large-scale statistical models require to estimate thousands to millions of parameters. This is often accomplished by iterative algorithms such as gradient descent, projected gradient descent or their accelerated versions. What are…

Machine Learning · Statistics 2020-03-04 Michael Celentano , Andrea Montanari , Yuchen Wu

Least squares approximation is a technique to find an approximate solution to a system of linear equations that has no exact solution. In a typical setting, one lets $n$ be the number of constraints and $d$ be the number of variables, with…

Data Structures and Algorithms · Computer Science 2010-09-28 Petros Drineas , Michael W. Mahoney , S. Muthukrishnan , Tamas Sarlos

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 goal of this paper is to show that a single robust estimator of the mean of a multivariate Gaussian distribution can enjoy five desirable properties. First, it is computationally tractable in the sense that it can be computed in a time…

Statistics Theory · Mathematics 2022-10-28 Arnak S. Dalalyan , Arshak Minasyan

The problem of matrix sensing, or trace regression, is a problem wherein one wishes to estimate a low-rank matrix from linear measurements perturbed with noise. A number of existing works have studied both convex and nonconvex approaches to…

Statistics Theory · Mathematics 2025-06-26 Joshua Agterberg , René Vidal

A subgradient method is presented for solving general convex optimization problems, the main requirement being that a strictly-feasible point is known. A feasible sequence of iterates is generated, which converges to within user-specified…

Optimization and Control · Mathematics 2016-05-30 James Renegar

Given a full rank matrix $X$ with more columns than rows, consider the task of estimating the pseudo inverse $X^+$ based on the pseudo inverse of a sampled subset of columns (of size at least the number of rows). We show that this is…

Machine Learning · Computer Science 2018-06-07 Michał Dereziński , Manfred K. Warmuth

We consider adaptive system identification problems with convex constraints and propose a family of regularized Least-Mean-Square (LMS) algorithms. We show that with a properly selected regularization parameter the regularized LMS provably…

Methodology · Statistics 2010-12-24 Yilun Chen , Yuantao Gu , Alfred O. Hero

We study the following basic machine learning task: Given a fixed set of $d$-dimensional input points for a linear regression problem, we wish to predict a hidden response value for each of the points. We can only afford to attain the…

Machine Learning · Computer Science 2018-06-07 Michał Dereziński , Manfred K. Warmuth

We consider the problem of estimating the mean of a noisy vector. When the mean lies in a convex constraint set, the least squares projection of the random vector onto the set is a natural estimator. Properties of the risk of this…

Statistics Theory · Mathematics 2017-06-15 Billy Fang , Adityanand Guntuboyina

It has been over 200 years since Gauss's and Legendre's famous priority dispute on who discovered the method of least squares. Nevertheless, we argue that the normal equations are still relevant in many facets of modern statistics,…

Statistics Theory · Mathematics 2013-10-01 Jonathan Taylor

We constraint on computer the best linear unbiased generalized statistics of random field for the best linear unbiased generalized statistics of an unknown constant mean of random field and derive the numerical generalized least-squares…

Numerical Analysis · Computer Science 2011-11-18 Tomasz Suslo

We study the problem of estimating the mean of a random vector $X$ given a sample of $N$ independent, identically distributed points. We introduce a new estimator that achieves a purely sub-Gaussian performance under the only condition that…

Statistics Theory · Mathematics 2017-02-03 Gábor Lugosi , Shahar Mendelson

We study the problem of variance estimation in general graph-structured problems. First, we develop a linear time estimator for the homoscedastic case that can consistently estimate the variance in general graphs. We show that our estimator…

Statistics Theory · Mathematics 2024-02-20 Oscar Hernan Madrid Padilla

In this paper we propose a general methodology, based on multiple testing, for testing that the mean of a Gaussian vector in R^n belongs to a convex set. We show that the test achieves its nominal level, and characterize a class of vectors…

Statistics Theory · Mathematics 2007-06-13 Yannick Baraud , Sylvie Huet , Beatrice Laurent

We consider the minimization of composite objective functions composed of the expectation of quadratic functions and an arbitrary convex function. We study the stochastic dual averaging algorithm with a constant step-size, showing that it…

Optimization and Control · Mathematics 2017-02-22 Nicolas Flammarion , Francis Bach

Researchers may perform regressions using a sketch of data of size $m$ instead of the full sample of size $n$ for a variety of reasons. This paper considers the case when the regression errors do not have constant variance and…

Machine Learning · Statistics 2022-06-23 Sokbae Lee , Serena Ng