English
Related papers

Related papers: Constructive regularization of the random matrix n…

200 papers

We develop a hierarchical matrix construction algorithm using matrix-vector multiplications, based on the randomized singular value decomposition of low-rank matrices. The algorithm uses $\mathcal{O}(\log n)$ applications of the matrix on…

Numerical Analysis · Mathematics 2010-08-24 Lin Lin , Jianfeng Lu , Lexing Ying

In many statistical learning problems, it is desired that the optimal solution conforms to an a priori known sparsity structure represented by a directed acyclic graph. Inducing such structures by means of convex regularizers requires…

Optimization and Control · Mathematics 2020-10-20 Dewei Zhang , Yin Liu , Sam Davanloo Tajbakhsh

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

The statistical leverage scores of a matrix $A$ are the squared row-norms of the matrix containing its (top) left singular vectors and the coherence is the largest leverage score. These quantities are of interest in recently-popular…

Data Structures and Algorithms · Computer Science 2012-12-06 Petros Drineas , Malik Magdon-Ismail , Michael W. Mahoney , David P. Woodruff

Several recent applications of optimal transport (OT) theory to machine learning have relied on regularization, notably entropy and the Sinkhorn algorithm. Because matrix-vector products are pervasive in the Sinkhorn algorithm, several…

Machine Learning · Statistics 2021-03-09 Meyer Scetbon , Marco Cuturi , Gabriel Peyré

Many data analysis applications deal with large matrices and involve approximating the matrix using a small number of ``components.'' Typically, these components are linear combinations of the rows and columns of the matrix, and are thus…

Data Structures and Algorithms · Computer Science 2007-08-29 Petros Drineas , Michael W. Mahoney , S. Muthukrishnan

In distributed second order optimization, a standard strategy is to average many local estimates, each of which is based on a small sketch or batch of the data. However, the local estimates on each machine are typically biased, relative to…

Machine Learning · Computer Science 2020-07-06 Michał Dereziński , Burak Bartan , Mert Pilanci , Michael W. Mahoney

In this paper, we consider optimal low-rank regularized inverse matrix approximations and their applications to inverse problems. We give an explicit solution to a generalized rank-constrained regularized inverse approximation problem,…

Numerical Analysis · Mathematics 2016-03-21 Julianne Chung , Matthias Chung

In this paper we study a worst case to average case reduction for the problem of matrix multiplication over finite fields. Suppose we have an efficient average case algorithm, that given two random matrices $A,B$ outputs a matrix that has a…

Data Structures and Algorithms · Computer Science 2024-04-15 Ashish Gola , Igor Shinkar , Harsimran Singh

We show how to compute a relative-error low-rank approximation to any positive semidefinite (PSD) matrix in sublinear time, i.e., for any $n \times n$ PSD matrix $A$, in $\tilde O(n \cdot poly(k/\epsilon))$ time we output a rank-$k$ matrix…

Data Structures and Algorithms · Computer Science 2019-01-04 Cameron Musco , David P. Woodruff

Recently, Musco and Woodruff (FOCS, 2017) showed that given an $n \times n$ positive semidefinite (PSD) matrix $A$, it is possible to compute a $(1+\epsilon)$-approximate relative-error low-rank approximation to $A$ by querying…

Data Structures and Algorithms · Computer Science 2021-06-16 Ainesh Bakshi , Nadiia Chepurko , David P. Woodruff

Regularization is a powerful technique for extracting useful information from noisy data. Typically, it is implemented by adding some sort of norm constraint to an objective function and then exactly optimizing the modified objective…

Data Structures and Algorithms · Computer Science 2011-04-28 Michael W. Mahoney , Lorenzo Orecchia

Given an arbitrary matrix $A\in\mathbb{R}^{n\times n}$, we consider the fundamental problem of computing $Ax$ for any $x\in\mathbb{R}^n$ such that $Ax$ is $s$-sparse. While fast algorithms exist for particular choices of $A$, such as the…

Computational Complexity · Computer Science 2021-05-14 Tim Fuchs , David Gross , Felix Krahmer , Richard Kueng , Dustin G. Mixon

We consider the problems of computing the optimal rank-$1$ Hankel and Toeplitz-structured approximation of arbitrary matrices under $L_2$ and $L_1$-norm error. Such problems arise naturally in engineered systems, including the basic…

Machine Learning · Computer Science 2026-05-07 Georgios I. Orfanidis

We consider fast algorithms for monotone submodular maximization with a general matroid constraint. We present a randomized $(1 - 1/e - \epsilon)$-approximation algorithm that requires $\tilde{O}_{\epsilon}(\sqrt{r} n)$ independence oracle…

Data Structures and Algorithms · Computer Science 2024-05-02 Yusuke Kobayashi , Tatsuya Terao

This paper focuses on recovering an underlying matrix from its noisy partial entries, a problem commonly known as matrix completion. We delve into the investigation of a non-convex regularization, referred to as transformed $L_1$ (TL1),…

Statistics Theory · Mathematics 2025-03-05 Kun Zhao , Jiayi Wang , Yifei Lou

In two earlier papers, we designed a distributed deterministic asynchronous algorithm for minimizing the sum of subdifferentiable and proximable functions and a regularizing quadratic on time-varying graphs based on Dykstra's algorithm, or…

Optimization and Control · Mathematics 2018-08-23 C. H. Jeffrey Pang

We show that any $n\times m$ matrix $A$ can be approximated in operator norm by a submatrix with a number of columns of order the stable rank of $A$. This improves on existing results by removing an extra logarithmic factor in the size of…

Functional Analysis · Mathematics 2018-07-19 Omer Friedland , Pierre Youssef

Given a matrix $M\in \mathbb{R}^{m\times n}$, the low rank matrix completion problem asks us to find a rank-$k$ approximation of $M$ as $UV^\top$ for $U\in \mathbb{R}^{m\times k}$ and $V\in \mathbb{R}^{n\times k}$ by only observing a few…

Machine Learning · Computer Science 2024-04-03 Yuzhou Gu , Zhao Song , Junze Yin , Lichen Zhang

We consider sketched approximate matrix multiplication and ridge regression in the novel setting of localized sketching, where at any given point, only part of the data matrix is available. This corresponds to a block diagonal structure on…

Machine Learning · Statistics 2020-03-23 Rakshith S Srinivasa , Mark A Davenport , Justin Romberg