English
Related papers

Related papers: Is Input Sparsity Time Possible for Kernel Low-Ran…

200 papers

Kernel $k$-means clustering can correctly identify and extract a far more varied collection of cluster structures than the linear $k$-means clustering algorithm. However, kernel $k$-means clustering is computationally expensive when the…

Machine Learning · Computer Science 2019-02-12 Shusen Wang , Alex Gittens , Michael W. Mahoney

$k$-Clustering in $\mathbb{R}^d$ (e.g., $k$-median and $k$-means) is a fundamental machine learning problem. While near-linear time approximation algorithms were known in the classical setting for a dataset with cardinality $n$, it remains…

Quantum Physics · Physics 2023-06-06 Yecheng Xue , Xiaoyu Chen , Tongyang Li , Shaofeng H. -C. Jiang

We consider relative error low rank approximation of $tensors$ with respect to the Frobenius norm: given an order-$q$ tensor $A \in \mathbb{R}^{\prod_{i=1}^q n_i}$, output a rank-$k$ tensor $B$ for which $\|A-B\|_F^2 \leq (1+\epsilon)$OPT,…

Data Structures and Algorithms · Computer Science 2018-04-02 Zhao Song , David P. Woodruff , Peilin Zhong

Kernel methods obtain superb performance in terms of accuracy for various machine learning tasks since they can effectively extract nonlinear relations. However, their time complexity can be rather large especially for clustering tasks. In…

Machine Learning · Statistics 2015-10-29 Xu Wang , Gilad Lerman

Imposing an effective structural assumption on neural network weight matrices has been the major paradigm for designing Parameter-Efficient Fine-Tuning (PEFT) systems for adapting modern large pre-trained models to various downstream tasks.…

Machine Learning · Computer Science 2025-02-20 Xin Li , Anand Sarwate

We provide guarantees for approximate Gaussian Process (GP) regression resulting from two common low-rank kernel approximations: based on random Fourier features, and based on truncating the kernel's Mercer expansion. In particular, we…

Machine Learning · Statistics 2022-02-22 Constantinos Daskalakis , Petros Dellaportas , Aristeidis Panos

We provide guarantees for approximate Gaussian Process (GP) regression resulting from two common low-rank kernel approximations: based on random Fourier features, and based on truncating the kernel's Mercer expansion. In particular, we…

Machine Learning · Statistics 2021-12-16 Constantinos Daskalakis , Petros Dellaportas , Aristeidis Panos

Kernel matrices appear in machine learning and non-parametric statistics. Given $N$ points in $d$ dimensions and a kernel function that requires $\mathcal{O}(d)$ work to evaluate, we present an $\mathcal{O}(dN\log N)$-work algorithm for the…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-01-11 Chenhan D. Yu , William B. March , George Biros

In this work, we propose a new randomized algorithm for computing a low-rank approximation to a given matrix. Taking an approach different from existing literature, our method first involves a specific biased sampling, with an element being…

Data Structures and Algorithms · Computer Science 2014-10-16 Srinadh Bhojanapalli , Prateek Jain , Sujay Sanghavi

In this paper, we derive entrywise error bounds for low-rank approximations of kernel matrices obtained using the truncated eigen-decomposition (or singular value decomposition). While this approximation is well-known to be optimal with…

Statistics Theory · Mathematics 2024-10-31 Alexander Modell

There are a number of approximation algorithms for NP-hard versions of low rank approximation, such as finding a rank-$k$ matrix $B$ minimizing the sum of absolute values of differences to a given $n$-by-$n$ matrix $A$,…

Data Structures and Algorithms · Computer Science 2020-04-20 Zhao Song , David P. Woodruff , Peilin Zhong

In this paper, we introduce a method for multivariate function approximation using function evaluations, Chebyshev polynomials, and tensor-based compression techniques via the Tucker format. We develop novel randomized techniques to…

Numerical Analysis · Mathematics 2021-07-29 Arvind K. Saibaba , Rachel Minster , Misha E. Kilmer

The randomly pivoted partial Cholesky algorithm (RPCholesky) computes a factorized rank-k approximation of an N x N positive-semidefinite (psd) matrix. RPCholesky requires only (k + 1) N entry evaluations and O(k^2 N) additional arithmetic…

Numerical Analysis · Mathematics 2024-10-23 Yifan Chen , Ethan N. Epperly , Joel A. Tropp , Robert J. Webber

We introduce kernel thinning, a new procedure for compressing a distribution $\mathbb{P}$ more effectively than i.i.d. sampling or standard thinning. Given a suitable reproducing kernel $\mathbf{k}_{\star}$ and $O(n^2)$ time, kernel…

Machine Learning · Statistics 2024-05-14 Raaz Dwivedi , Lester Mackey

In the iterative solution of dense linear systems from boundary integral equations or systems involving kernel matrices, the main challenges are the expensive matrix-vector multiplication and the storage cost which are usually tackled by…

Numerical Analysis · Mathematics 2018-11-13 Xin Xing , Edmond Chow

Gaussian processes are powerful models for probabilistic machine learning, but are limited in application by their $O(N^3)$ inference complexity. We propose a method for deriving parametric families of kernel functions with compact spatial…

Machine Learning · Computer Science 2020-06-09 Jarred Barber

We consider the problem of approximating an affinely structured matrix, for example a Hankel matrix, by a low-rank matrix with the same structure. This problem occurs in system identification, signal processing and computer algebra, among…

Numerical Analysis · Mathematics 2014-06-25 Mariya Ishteva , Konstantin Usevich , Ivan Markovsky

This work studies low-rank approximation of a positive semidefinite matrix from partial entries via nonconvex optimization. We characterized how well local-minimum based low-rank factorization approximates a fixed positive semidefinite…

Optimization and Control · Mathematics 2019-04-08 Ji Chen , Xiaodong Li

A common data analysis task is the reduced-rank regression problem: $$\min_{\textrm{rank-}k \ X} \|AX-B\|,$$ where $A \in \mathbb{R}^{n \times c}$ and $B \in \mathbb{R}^{n \times d}$ are given large matrices and $\|\cdot\|$ is some norm.…

Data Structures and Algorithms · Computer Science 2021-07-02 Praneeth Kacham , David P. Woodruff

We show how to solve a number of problems in numerical linear algebra, such as least squares regression, $\ell_p$-regression for any $p \geq 1$, low rank approximation, and kernel regression, in time $T(A) \poly(\log(nd))$, where for a…

Machine Learning · Computer Science 2019-12-13 Xiaofei Shi , David P. Woodruff