English
Related papers

Related papers: Leverage Score Sampling for Faster Accelerated Reg…

200 papers

Low-rank tensor decomposition generalizes low-rank matrix approximation and is a powerful technique for discovering low-dimensional structure in high-dimensional data. In this paper, we study Tucker decompositions and use tools from…

Data Structures and Algorithms · Computer Science 2021-07-23 Matthew Fahrbach , Mehrdad Ghadiri , Thomas Fu

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

We consider the problem of exact recovery of any $m\times n$ matrix of rank $\varrho$ from a small number of observed entries via the standard nuclear norm minimization framework. Such low-rank matrices have degrees of freedom $(m+n)\varrho…

Information Theory · Computer Science 2016-04-08 Abhisek Kundu

We focus the use of \emph{row sampling} for approximating matrix algorithms. We give applications to matrix multipication; sparse matrix reconstruction; and, \math{\ell_2} regression. For a matrix \math{\matA\in\R^{m\times d}} which…

Data Structures and Algorithms · Computer Science 2010-08-04 Malik Magdon-Ismail

Tensor Train~(TT) decomposition is widely used in the machine learning and quantum physics communities as a popular tool to efficiently compress high-dimensional tensor data. In this paper, we propose an efficient algorithm to accelerate…

Data Structures and Algorithms · Computer Science 2024-06-07 Vivek Bharadwaj , Beheshteh T. Rakhshan , Osman Asif Malik , Guillaume Rabusseau

We design a new distribution over $\poly(r \eps^{-1}) \times n$ matrices $S$ so that for any fixed $n \times d$ matrix $A$ of rank $r$, with probability at least 9/10, $\norm{SAx}_2 = (1 \pm \eps)\norm{Ax}_2$ simultaneously for all $x \in…

Data Structures and Algorithms · Computer Science 2013-04-08 Kenneth L. Clarkson , David P. Woodruff

We provide faster algorithms and improved sample complexities for approximating the top eigenvector of a matrix. Offline Setting: Given an $n \times d$ matrix $A$, we show how to compute an $\epsilon$ approximate top eigenvector in time…

Data Structures and Algorithms · Computer Science 2016-05-31 Chi Jin , Sham M. Kakade , Cameron Musco , Praneeth Netrapalli , Aaron Sidford

For a matrix $A\in \mathbb{R}^{n\times d}$ with $n\geq d$, we consider the dual problems of $\min \|Ax-b\|_p^p, \, b\in \mathbb{R}^n$ and $\min_{A^\top x=b} \|x\|_p^p,\, b\in \mathbb{R}^d$. We improve the runtimes for solving these problems…

Data Structures and Algorithms · Computer Science 2021-11-22 Mehrdad Ghadiri , Richard Peng , Santosh S. Vempala

We give improved algorithms for the $\ell_{p}$-regression problem, $\min_{x} \|x\|_{p}$ such that $A x=b,$ for all $p \in (1,2) \cup (2,\infty).$ Our algorithms obtain a high accuracy solution in $\tilde{O}_{p}(m^{\frac{|p-2|}{2p + |p-2|}})…

Data Structures and Algorithms · Computer Science 2024-12-20 Deeksha Adil , Rasmus Kyng , Richard Peng , Sushant Sachdeva

We propose an input sparsity time sampling algorithm that can spectrally approximate the Gram matrix corresponding to the $q$-fold column-wise tensor product of $q$ matrices using a nearly optimal number of samples, improving upon all…

Machine Learning · Computer Science 2022-06-27 David P. Woodruff , Amir Zandieh

We develop a new efficient sequential approximate leverage score algorithm, SALSA, using methods from randomized numerical linear algebra (RandNLA) for large matrices. We demonstrate that, with high probability, the accuracy of SALSA's…

Machine Learning · Statistics 2024-01-02 Ali Eshragh , Luke Yerbury , Asef Nazari , Fred Roosta , Michael W. Mahoney

This paper investigates the optimal ergodic sublinear convergence rate of the relaxed proximal point algorithm for solving monotone variational inequality problems. The exact worst case convergence rate is computed using the performance…

Optimization and Control · Mathematics 2019-07-15 Guoyong Gu , Junfeng Yang

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

This paper considers the sample-efficiency of preference learning, which models and predicts human choices based on comparative judgments. The minimax optimal estimation error rate $\Theta(d/n)$ in classical estimation theory requires that…

Machine Learning · Computer Science 2025-06-05 Yunzhen Yao , Lie He , Michael Gastpar

The demand of computational resources for the modeling process increases as the scale of the datasets does, since traditional approaches for regression involve inverting huge data matrices. The main problem relies on the large data size,…

Methodology · Statistics 2023-07-06 Vasilis Chasiotis , Dimitris Karlis

One approach to improving the running time of kernel-based machine learning methods is to build a small sketch of the input and use it in lieu of the full kernel matrix in the machine learning task of interest. Here, we describe a version…

Machine Learning · Statistics 2015-11-10 Ahmed El Alaoui , Michael W. Mahoney

In the total least squares problem, one is given an $m \times n$ matrix $A$, and an $m \times d$ matrix $B$, and one seeks to "correct" both $A$ and $B$, obtaining matrices $\hat{A}$ and $\hat{B}$, so that there exists an $X$ satisfying the…

Data Structures and Algorithms · Computer Science 2019-09-30 Huaian Diao , Zhao Song , David P. Woodruff , Xin Yang

We compute a \emph{sparse} solution to the classical least-squares problem $\min_x||A x -b||,$ where $A$ is an arbitrary matrix. We describe a novel algorithm for this sparse least-squares problem. The algorithm operates as follows: first,…

Data Structures and Algorithms · Computer Science 2013-12-31 Christos Boutsidis , Malik Magdon-Ismail

Leverage score sampling is a powerful technique that originates from theoretical computer science, which can be used to speed up a large number of fundamental questions, e.g. linear regression, linear programming, semi-definite programming,…

Machine Learning · Computer Science 2020-09-22 Jason D. Lee , Ruoqi Shen , Zhao Song , Mengdi Wang , Zheng Yu

The low-rank canonical polyadic tensor decomposition is useful in data analysis and can be computed by solving a sequence of overdetermined least squares subproblems. Motivated by consideration of sparse tensors, we propose sketching each…

Numerical Analysis · Mathematics 2022-01-05 Brett W. Larsen , Tamara G. Kolda