English
Related papers

Related papers: A Nearly-Optimal Bound for Fast Regression with $\…

200 papers

The iteratively reweighted least squares method (IRLS) is a popular technique used in practice for solving regression problems. Various versions of this method have been proposed, but their theoretical analyses failed to capture the good…

Data Structures and Algorithms · Computer Science 2019-07-11 Alina Ene , Adrian Vladu

Consider the standard linear regression model $\y = \Xmat \betastar + w$, where $\y \in \real^\numobs$ is an observation vector, $\Xmat \in \real^{\numobs \times \pdim}$ is a design matrix, $\betastar \in \real^\pdim$ is the unknown…

Statistics Theory · Mathematics 2010-09-14 Garvesh Raskutti , Martin J. Wainwright , Bin Yu

We consider the fundamental problem of estimating the mean of a vector $y=X\beta+z$, where $X$ is an $n\times p$ design matrix in which one can have far more variables than observations, and $z$ is a stochastic error term--the so-called…

Statistics Theory · Mathematics 2009-08-21 Emmanuel J. Candès , Yaniv Plan

Online learning algorithms require to often recompute least squares regression estimates of parameters. We study improving the computational complexity of such algorithms by using stochastic gradient descent (SGD) type schemes in place of…

Machine Learning · Computer Science 2014-11-21 Nathaniel Korda , Prashanth L. A. , Rémi Munos

Leveraging the kernel trick in both the input and output spaces, surrogate kernel methods are a flexible and theoretically grounded solution to structured output prediction. If they provide state-of-the-art performance on complex data sets…

Machine Learning · Statistics 2024-05-07 Tamim El Ahmad , Luc Brogat-Motte , Pierre Laforgue , Florence d'Alché-Buc

Maximum coverage and minimum set cover problems --collectively called coverage problems-- have been studied extensively in streaming models. However, previous research not only achieve sub-optimal approximation factors and space…

Data Structures and Algorithms · Computer Science 2017-03-13 Mohammadhossein Bateni , Hossein Esfandiari , Vahab Mirrokni

Matrix sensing is a problem in signal processing and machine learning that involves recovering a low-rank matrix from a set of linear measurements. The goal is to reconstruct the original matrix as accurately as possible, given only a set…

Information Theory · Computer Science 2023-03-14 Yichuan Deng , Zhihang Li , Zhao Song

We demonstrate that the best $k$-sparse approximation of a length-$n$ vector can be recovered within a $(1+\epsilon)$-factor approximation in $O((k/\epsilon) \log n)$ time using a non-adaptive linear sketch with $O((k/\epsilon) \log n)$…

Data Structures and Algorithms · Computer Science 2025-10-24 Nick Fischer , Vasileios Nakos

We propose a sparse deep ReLU network (SDRN) estimator of the regression function obtained from regularized empirical risk minimization with a Lipschitz loss function. Our framework can be applied to a variety of regression and…

Methodology · Statistics 2024-12-11 Ke Huang , Mingming Liu , Shujie Ma

Most sequence sketching methods work by selecting specific $k$-mers from sequences so that the similarity between two sequences can be estimated using only the sketches. Estimating sequence similarity is much faster using sketches than…

Data Structures and Algorithms · Computer Science 2023-11-08 Guillaume Marçais , Dan DeBlasio , Carl Kingsford

We give a new framework for solving the fundamental problem of low-rank matrix completion, i.e., approximating a rank-$r$ matrix $\mathbf{M} \in \mathbb{R}^{m \times n}$ (where $m \ge n$) from random observations. First, we provide an…

Machine Learning · Computer Science 2023-08-08 Jonathan A. Kelner , Jerry Li , Allen Liu , Aaron Sidford , Kevin Tian

SketchySGD improves upon existing stochastic gradient methods in machine learning by using randomized low-rank approximations to the subsampled Hessian and by introducing an automated stepsize that works well across a wide range of convex…

Optimization and Control · Mathematics 2024-02-22 Zachary Frangella , Pratik Rathore , Shipu Zhao , Madeleine Udell

Kernel matrices, as well as weighted graphs represented by them, are ubiquitous objects in machine learning, statistics and other related fields. The main drawback of using kernel methods (learning and inference using kernel matrices) is…

Machine Learning · Computer Science 2022-12-02 Ainesh Bakshi , Piotr Indyk , Praneeth Kacham , Sandeep Silwal , Samson Zhou

Motivated by a sampling problem basic to computational statistical inference, we develop a nearly optimal algorithm for a fundamental problem in spectral graph theory and numerical analysis. Given an $n\times n$ SDDM matrix ${\bf…

Data Structures and Algorithms · Computer Science 2014-10-21 Dehua Cheng , Yu Cheng , Yan Liu , Richard Peng , Shang-Hua Teng

In this paper, assuming the low-degree conjecture, we provide evidence of computational hardness for two problems: (1) the (partial) matching recovery problem in the sparse correlated Erd\H{o}s-R\'enyi graphs $\mathcal G(n,q;\rho)$ when the…

Machine Learning · Statistics 2025-12-30 Zhangsong Li

We explore algorithms and limitations for sparse optimization problems such as sparse linear regression and robust linear regression. The goal of the sparse linear regression problem is to identify a small number of key features, while the…

Machine Learning · Computer Science 2022-06-30 Eric Price , Sandeep Silwal , Samson Zhou

In this paper we consider large-scale smooth optimization problems with multiple linear coupled constraints. Due to the non-separability of the constraints, arbitrary random sketching would not be guaranteed to work. Thus, we first…

Optimization and Control · Mathematics 2018-08-09 Ion Necoara , Martin Takac

Among randomized numerical linear algebra strategies, so-called sketching procedures are emerging as effective reduction means to accelerate the computation of Krylov subspace methods for, e.g., the solution of linear systems, eigenvalue…

Numerical Analysis · Mathematics 2024-08-02 Davide Palitta , Marcel Schweitzer , Valeria Simoncini

In this paper we study constrained subspace approximation problem. Given a set of $n$ points $\{a_1,\ldots,a_n\}$ in $\mathbb{R}^d$, the goal of the {\em subspace approximation} problem is to find a $k$ dimensional subspace that best…

Data Structures and Algorithms · Computer Science 2025-04-30 Aditya Bhaskara , Sepideh Mahabadi , Madhusudhan Reddy Pittu , Ali Vakilian , David P. Woodruff

We provide the first nearly-linear time algorithm for approximating $\ell_{q \rightarrow p}$-norms of non-negative matrices, for $q \geq p \geq 1$. Our algorithm returns a $(1-\varepsilon)$-approximation to the matrix norm in time…

Data Structures and Algorithms · Computer Science 2025-03-26 Étienne Objois , Adrian Vladu