English
Related papers

Related papers: Gaussian Sketching yields a J-L Lemma in RKHS

200 papers

We present an extension of an adaptive, partially matrix-free, Hierarchically Semi-Separable (HSS) matrix construction algorithm by Gorman et al. [SIAM J. Sci. Comput. 41(5), 2019] which uses Gaussian sketching operators to a broader class…

Numerical Analysis · Mathematics 2025-11-26 Yotam Yaniv , Pieter Ghysels , Osman Asif Malik , Henry A. Boateng , Xiaoye S. Li

The Grassmannian manifold G(k, n) serves as a fundamental tool in signal processing, computer vision, and machine learning, where problems often involve classifying, clustering, or comparing subspaces. In this work, we propose a…

Signal Processing · Electrical Eng. & Systems 2025-05-01 Rémi Delogne , Laurent Jacques

Kernel methods are learning algorithms that enjoy solid theoretical foundations while suffering from important computational limitations. Sketching, which consists in looking for solutions among a subspace of reduced dimension, is a well…

Machine Learning · Statistics 2023-11-07 Tamim El Ahmad , Pierre Laforgue , Florence d'Alché-Buc

Influence functions and related data attribution scores take the form of $g^{\top}F^{-1}g^{\prime}$, where $F\succeq 0$ is a curvature operator. In modern overparametrized models, forming or inverting $F\in\mathbb{R}^{d\times d}$ is…

Machine Learning · Computer Science 2026-02-16 Pingbang Hu , Yuzheng Hu , Jiaqi W. Ma , Han Zhao

We develop a stochastic approximation framework for learning nonlinear operators between infinite-dimensional spaces utilizing general Mercer operator-valued kernels. Our framework encompasses two key classes: (i) compact kernels, which…

Machine Learning · Statistics 2026-01-13 Jia-Qi Yang , Lei Shi

We propose a new random sketching approach for embedding high-dimensional Hilbert-Schmidt operators, using random input-output pairs. Such operator can then be approximated in a low-dimensional subspace of operators by solving a small…

Numerical Analysis · Mathematics 2026-04-15 Oleg Balabanov , Anthony Nouy , Alexandre Pasco

Learning parameters from voluminous data can be prohibitive in terms of memory and computational requirements. We propose a "compressive learning" framework where we estimate model parameters from a sketch of the training data. This sketch…

Machine Learning · Computer Science 2017-05-08 Nicolas Keriven , Anthony Bourrier , Rémi Gribonval , Patrick Pérez

We propose and study kernel conjugate gradient methods (KCGM) with random projections for least-squares regression over a separable Hilbert space. Considering two types of random projections generated by randomized sketches and Nystr\"{o}m…

Machine Learning · Statistics 2022-07-18 Junhong Lin , Volkan Cevher

Algorithmic Gaussianization is a phenomenon that can arise when using randomized sketching or sampling methods to produce smaller representations of large datasets: For certain tasks, these sketched representations have been observed to…

Machine Learning · Computer Science 2023-07-28 Michał Dereziński

Understanding the stochastic behavior of random projections of geometric sets constitutes a fundamental problem in high dimension probability that finds wide applications in diverse fields. This paper provides a kinematic description for…

Probability · Mathematics 2026-03-17 Qiyang Han , Huachen Ren

We introduce a technique for estimating a structured covariance matrix from observations of a random vector which have been sketched. Each observed random vector $\boldsymbol{x}_t$ is reduced to a single number by taking its inner product…

Information Theory · Computer Science 2015-10-09 Sohail Bahmani , Justin Romberg

In this paper we make a novel use of the Johnson-Lindenstrauss Lemma. The Lemma has an existential form saying that there exists a JL transformation $f$ of the data points into lower dimensional space such that all of them fall into…

Data Structures and Algorithms · Computer Science 2017-11-10 Mieczysław A. Kłopotek

This article focuses on drawing computationally-efficient predictive inference from Gaussian process (GP) regressions with a large number of features when the response is conditionally independent of the features given the projection to a…

Methodology · Statistics 2024-09-27 Samuel Gailliot , Rajarshi Guhaniyogi , Roger D. Peng

We present simple, user-friendly bounds for the expected operator norm of a random kernel matrix under general conditions on the kernel function $k(\cdot,\cdot)$. Our approach uses decoupling results for U-statistics and the non-commutative…

Machine Learning · Statistics 2025-11-07 Chiraag Kaushik , Justin Romberg , Vidya Muthukumar

When $G$ is a complex reductive algebraic group and $G/K$ is a reductive symmetric space, the decomposition of $\C[G/K]$ as a $K$-module was obtained (in a non-constructive way) by Richardson, generalizing the celebrated result of…

Representation Theory · Mathematics 2007-05-23 Ilka Agricola , Roe Goodman

Count-sketch is a popular matrix sketching algorithm that can produce a sketch of an input data matrix X in O(nnz(X))time where nnz(X) denotes the number of non-zero entries in X. The sketched matrix will be much smaller than X while…

Machine Learning · Computer Science 2020-11-30 Yuhan Wang , Zijian Lei , Liang Lan

Random projections or sketching are widely used in many algorithmic and learning contexts. Here we study the performance of iterative Hessian sketch for least-squares problems. By leveraging and extending recent results from random matrix…

Optimization and Control · Mathematics 2020-10-26 Jonathan Lacotte , Sifan Liu , Edgar Dobriban , Mert Pilanci

The Johnson--Lindenstrauss (JL) lemma is a powerful tool for dimensionality reduction in modern algorithm design. The lemma states that any set of high-dimensional points in a Euclidean space can be flattened to lower dimensions while…

Probability · Mathematics 2024-11-08 Kwassi Joseph Dzahini , Stefan M. Wild

The Johnson-Lindenstrauss Lemma states that there exist linear maps that project a set of points of a vector space into a space of much lower dimension such that the Euclidean distance between these points is approximately preserved. This…

Optimization and Control · Mathematics 2023-01-18 Pierre-Louis Poirion , Bruno F. Lourenço , Akiko Takeda

We present a theoretically grounded Gaussian process framework that leverages neural feature maps to construct expressive kernels. We show that the learned feature map can be interpreted as an optimal low-rank approximation to a Gram matrix…

Machine Learning · Statistics 2026-05-12 Anthony Stephenson
‹ Prev 1 2 3 10 Next ›