English
Related papers

Related papers: Streaming Kernel PCA with $\tilde{O}(\sqrt{n})$ Ra…

200 papers

Fair Principal Component Analysis (PCA) is a problem setting where we aim to perform PCA while making the resulting representation fair in that the projected distributions, conditional on the sensitive attributes, match one another.…

Machine Learning · Statistics 2023-10-31 Junghyun Lee , Hanseul Cho , Se-Young Yun , Chulhee Yun

We study the generalization properties of ridge regression with random features in the statistical learning framework. We show for the first time that $O(1/\sqrt{n})$ learning bounds can be achieved with only $O(\sqrt{n}\log n)$ random…

Machine Learning · Statistics 2021-04-16 Alessandro Rudi , Lorenzo Rosasco

Oja's algorithm has been the cornerstone of streaming methods in Principal Component Analysis (PCA) since it was first proposed in 1982. However, Oja's algorithm does not have a standardized choice of learning rate (step size) that both…

Machine Learning · Statistics 2019-11-04 Amelia Henriksen , Rachel Ward

We study principal component analysis (PCA), where given a dataset in $\mathbb{R}^d$ from a distribution, the task is to find a unit vector $v$ that approximately maximizes the variance of the distribution after being projected along $v$.…

Machine Learning · Computer Science 2023-05-05 Ilias Diakonikolas , Daniel M. Kane , Ankit Pensia , Thanasis Pittas

We initiate a broad study of classical problems in the streaming model with insertions and deletions in the setting where we allow the approximation factor $\alpha$ to be much larger than $1$. Such algorithms can use significantly less…

Data Structures and Algorithms · Computer Science 2022-07-19 Yi Li , Honghao Lin , David P. Woodruff , Yuheng Zhang

The distinct elements problem is one of the fundamental problems in streaming algorithms --- given a stream of integers in the range $\{1,\ldots,n\}$, we wish to provide a $(1+\varepsilon)$ approximation to the number of distinct elements…

Data Structures and Algorithms · Computer Science 2019-01-07 Jarosław Błasiok

Motivated by a fundamental paradigm in cryptography, we consider a recent variant of the classic problem of bounding the distinguishing advantage between a random function and a random permutation. Specifically, we consider the problem of…

Information Theory · Computer Science 2020-04-22 Ido Shahaf , Or Ordentlich , Gil Segev

Cryo-electron microscopy nowadays often requires the analysis of hundreds of thousands of 2D images as large as a few hundred pixels in each direction. Here we introduce an algorithm that efficiently and accurately performs principal…

Computer Vision and Pattern Recognition · Computer Science 2015-12-16 Zhizhen Zhao , Yoel Shkolnisky , Amit Singer

Kernel methods are powerful learning methodologies that allow to perform non-linear data analysis. Despite their popularity, they suffer from poor scalability in big data scenarios. Various approximation methods, including random feature…

Machine Learning · Statistics 2022-06-14 Bharath Sriperumbudur , Nicholas Sterge

Streaming algorithms are generally judged by the quality of their solution, memory footprint, and computational complexity. In this paper, we study the problem of maximizing a monotone submodular function in the streaming setting with a…

Machine Learning · Computer Science 2019-05-14 Ehsan Kazemi , Marko Mitrovic , Morteza Zadimoghaddam , Silvio Lattanzi , Amin Karbasi

We consider the problem of monotone, submodular maximization over a ground set of size $n$ subject to cardinality constraint $k$. For this problem, we introduce the first deterministic algorithms with linear time complexity; these…

Data Structures and Algorithms · Computer Science 2021-03-09 Alan Kuhnle

Kernel methods have recently attracted resurgent interest, showing performance competitive with deep neural networks in tasks such as speech recognition. The random Fourier features map is a technique commonly used to scale up kernel…

Machine Learning · Computer Science 2018-02-01 Tri Dao , Christopher De Sa , Christopher Ré

Tensor algebras give rise to one of the most powerful measures of similarity for sequences of arbitrary length called the signature kernel accompanied with attractive theoretical guarantees from stochastic analysis. Previous algorithms to…

Machine Learning · Statistics 2024-11-25 Csaba Toth , Harald Oberhauser , Zoltan Szabo

Kernel Principal Component Analysis (KPCA) is a key machine learning algorithm for extracting nonlinear features from data. In the presence of a large volume of high dimensional data collected in a distributed fashion, it becomes very…

Machine Learning · Computer Science 2016-02-16 Maria-Florina Balcan , Yingyu Liang , Le Song , David Woodruff , Bo Xie

We consider the classic Euclidean $k$-median and $k$-means objective on data streams, where the goal is to provide a $(1+\varepsilon)$-approximation to the optimal $k$-median or $k$-means solution, while using as little memory as possible.…

Data Structures and Algorithms · Computer Science 2023-10-05 Vincent Cohen-Addad , David P. Woodruff , Samson Zhou

Oja's algorithm of principal component analysis (PCA) has been one of the methods utilized in practice to reduce dimension. In this paper, we focus on the convergence property of the discrete algorithm. To realize that, we view the…

Numerical Analysis · Mathematics 2023-01-05 Jian-Guo Liu , Zibu Liu

We initiate the investigation of the parameterized complexity of Diameter and Connectivity in the streaming paradigm. On the positive end, we show that knowing a vertex cover of size $k$ allows for algorithms in the Adjacency List (AL)…

Data Structures and Algorithms · Computer Science 2024-07-19 Jelle J. Oostveen , Erik Jan van Leeuwen

Principal Component Analysis (PCA) is a popular method for dimension reduction and has attracted an unfailing interest for decades. More recently, kernel PCA (KPCA) has emerged as an extension of PCA but, despite its use in practice, a…

Machine Learning · Computer Science 2023-01-25 Maxime Haddouche , Benjamin Guedj , John Shawe-Taylor

We propose a principled method for kernel learning, which relies on a Fourier-analytic characterization of translation-invariant or rotation-invariant kernels. Our method produces a sequence of feature maps, iteratively refining the SVM…

Machine Learning · Computer Science 2018-02-28 Brian Bullins , Cyril Zhang , Yi Zhang

Kernel methods provide an elegant framework for developing nonlinear learning algorithms from simple linear methods. Though these methods have superior empirical performance in several real data applications, their usefulness is inhibited…

Machine Learning · Statistics 2021-05-20 Nicholas Sterge , Bharath Sriperumbudur