English
Related papers

Related papers: Almost Linear Constant-Factor Sketching for $\ell_…

200 papers

For a tall $n\times d$ matrix $A$ and a random $m\times n$ sketching matrix $S$, the sketched estimate of the inverse covariance matrix $(A^\top A)^{-1}$ is typically biased: $E[(\tilde A^\top\tilde A)^{-1}]\ne(A^\top A)^{-1}$, where…

Data Structures and Algorithms · Computer Science 2021-07-13 Michał Dereziński , Zhenyu Liao , Edgar Dobriban , Michael W. Mahoney

Motivated by the study of matrix elimination orderings in combinatorial scientific computing, we utilize graph sketching and local sampling to give a data structure that provides access to approximate fill degrees of a matrix undergoing…

Data Structures and Algorithms · Computer Science 2023-04-11 Matthew Fahrbach , Gary L. Miller , Richard Peng , Saurabh Sawlani , Junxing Wang , Shen Chen Xu

We provide $m^{1+o(1)}k\epsilon^{-1}$-time algorithms for computing multiplicative $(1 - \epsilon)$-approximate solutions to multi-commodity flow problems with $k$-commodities on $m$-edge directed graphs, including concurrent…

Data Structures and Algorithms · Computer Science 2025-04-01 Li Chen , Andrei Graur , Aaron Sidford

We consider a continual learning (CL) problem with two linear regression tasks in the fixed design setting, where the feature vectors are assumed fixed and the labels are assumed to be random variables. We consider an $\ell_2$-regularized…

Machine Learning · Computer Science 2024-06-19 Haoran Li , Jingfeng Wu , Vladimir Braverman

We introduce two versions of a new sketch for approximately embedding the Gaussian kernel into Euclidean inner product space. These work by truncating infinite expansions of the Gaussian kernel, and carefully invoking the…

Machine Learning · Computer Science 2020-06-22 Jeff M. Phillips , Wai Ming Tai

We introduce a new sub-linear space sketch---the Weight-Median Sketch---for learning compressed linear classifiers over data streams while supporting the efficient recovery of large-magnitude weights in the model. This enables…

Machine Learning · Computer Science 2018-04-10 Kai Sheng Tai , Vatsal Sharan , Peter Bailis , Gregory Valiant

We provide a deterministic space-efficient algorithm for estimating ridge regression. For $n$ data points with $d$ features and a large enough regularization parameter, we provide a solution within $\varepsilon$ L$_2$ error using only…

Machine Learning · Computer Science 2021-06-29 Benwei Shi , Jeff M. Phillips

We develop and analyze stochastic optimization algorithms for problems in which the expected loss is strongly convex, and the optimum is (approximately) sparse. Previous approaches are able to exploit only one of these two structures,…

Machine Learning · Statistics 2012-07-19 Alekh Agarwal , Sahand Negahban , Martin J. Wainwright

We study randomized sketching methods for approximately solving least-squares problem with a general convex constraint. The quality of a least-squares approximation can be assessed in different ways: either in terms of the value of the…

Optimization and Control · Mathematics 2014-11-04 Mert Pilanci , Martin J. Wainwright

An outstanding open question posed by Guha and Indyk in 2006 asks to characterize metric spaces in which distances can be estimated using efficient sketches. Specifically, we say that a sketching algorithm is efficient if it achieves…

Data Structures and Algorithms · Computer Science 2017-02-16 Alexandr Andoni , Robert Krauthgamer , Ilya Razenshteyn

The cost of both generalized least squares (GLS) and Gibbs sampling in a crossed random effects model can easily grow faster than $N^{3/2}$ for $N$ observations. Ghosh et al. (2020) develop a backfitting algorithm that reduces the cost to…

Methodology · Statistics 2021-12-30 Swarnadip Ghosh , Trevor Hastie , Art B. Owen

Sketch-and-solve (SAS) is a very successful method to efficiently estimate the solution of heavily overdetermined large linear least squares problems. It uses random sketching to reduce the size of the problem, hence reducing the…

Numerical Analysis · Mathematics 2026-05-26 Irina-Beatrice Haas , Michael B. Giles , Yuji Nakatsukasa

We revisit the problem of sketching using approximate leverage scores for matrix least squares problems of the form $\| AX - B \|_F^2$ where the design matrix $A \in \mathbb{R}^{N \times r}$ is tall and skinny with $N \gg r$. We derive the…

Numerical Analysis · Mathematics 2026-03-31 Brett W. Larsen , Tamara G. Kolda

We derive optimal statistical and computational complexity bounds for exp-concave stochastic minimization in terms of the effective dimension. For common eigendecay patterns of the population covariance matrix, this quantity is…

Machine Learning · Computer Science 2019-09-24 Naman Agarwal , Alon Gonen

We provide fast algorithms for overconstrained $\ell_p$ regression and related problems: for an $n\times d$ input matrix $A$ and vector $b\in\mathbb{R}^n$, in $O(nd\log n)$ time we reduce the problem $\min_{x\in\mathbb{R}^d} \|Ax-b\|_p$ to…

Data Structures and Algorithms · Computer Science 2014-04-08 Kenneth L. Clarkson , Petros Drineas , Malik Magdon-Ismail , Michael W. Mahoney , Xiangrui Meng , David P. Woodruff

We analyze the sketching approximability of constraint satisfaction problems on Boolean domains, where the constraints are balanced linear threshold functions applied to literals. In~particular, we explore the approximability of…

Computational Complexity · Computer Science 2022-07-18 Chi-Ning Chou , Alexander Golovnev , Amirbehshad Shahrasbi , Madhu Sudan , Santhoshini Velusamy

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

Datasets with sheer volume have been generated from fields including computer vision, medical imageology, and astronomy whose large-scale and high-dimensional properties hamper the implementation of classical statistical models. To tackle…

Statistics Theory · Mathematics 2023-05-30 Hang Yu , Zhenxing Dou , Zhiwei Chen , Xiaomeng Yan

We consider the problem of maximizing a monotone submodular function subject to a knapsack constraint. Our main contribution is an algorithm that achieves a nearly-optimal, $1 - 1/e - \epsilon$ approximation, using…

Data Structures and Algorithms · Computer Science 2018-11-20 Alina Ene , Huy L. Nguyen

Recently, linear regression models incorporating an optimal transport (OT) loss have been explored for applications such as supervised unmixing of spectra, music transcription, and mass spectrometry. However, these task-specific approaches…