English
Related papers

Related papers: Relative Error Embeddings for the Gaussian Kernel …

200 papers

Random features have been introduced to scale up kernel methods via randomization techniques. In particular, random Fourier features and orthogonal random features were used to approximate the popular Gaussian kernel. Random Fourier…

Machine Learning · Computer Science 2024-10-22 Nizar Demni , Hachem Kadri

A Hilbert space embedding of a distribution---in short, a kernel mean embedding---has recently emerged as a powerful tool for machine learning and inference. The basic idea behind this framework is to map distributions into a reproducing…

Machine Learning · Statistics 2020-12-15 Krikamol Muandet , Kenji Fukumizu , Bharath Sriperumbudur , Bernhard Schölkopf

Gaussian Radial Basis Function (RBF) Kernels are the most-often-employed kernels in artificial intelligence and machine learning routines for providing optimally-best results in contrast to their respective counter-parts. However, a little…

Machine Learning · Computer Science 2023-12-19 Himanshu Singh

Approximation using Fourier features is a popular technique for scaling kernel methods to large-scale problems, with myriad applications in machine learning and statistics. This method replaces the integral representation of a…

Machine Learning · Statistics 2024-08-26 Ayoub Belhadji , Qianyu Julie Zhu , Youssef Marzouk

The sample complexity of estimating or maximising an unknown function in a reproducing kernel Hilbert space is known to be linked to both the effective dimension and the information gain associated with the kernel. While the information…

Machine Learning · Statistics 2026-01-16 Hamish Flynn

This paper introduces algorithms to select/design kernels in Gaussian process regression/kriging surrogate modeling techniques. We adopt the setting of kernel method solutions in ad hoc functional spaces, namely Reproducing Kernel Hilbert…

Machine Learning · Statistics 2022-09-07 Jean-Luc Akian , Luc Bonnet , Houman Owhadi , Éric Savin

We prove that kernel covariance embeddings lead to information-theoretically perfect separation of distinct continuous probability distributions. In statistical terms, we establish that testing for the \emph{equality} of two non-atomic…

Machine Learning · Statistics 2026-05-14 Leonardo V. Santoro , Kartik G. Waghmare , Victor M. Panaretos

Random feature neural network approximations of the potential in Hamiltonian systems yield approximations of molecular dynamics correlation observables that have the expected error $\mathcal{O}\big((K^{-1}+J^{-1/2})^{\frac{1}{2}}\big)$, for…

Numerical Analysis · Mathematics 2024-06-24 Xin Huang , Petr Plechac , Mattias Sandberg , Anders Szepessy

We study the construction of coresets for kernel density estimates. That is we show how to approximate the kernel density estimate described by a large point set with another kernel density estimate with a much smaller point set. For…

Machine Learning · Computer Science 2017-10-13 Jeff M. Phillips , Wai Ming Tai

This monograph studies the relations between two approaches using positive definite kernels: probabilistic methods using Gaussian processes, and non-probabilistic methods using reproducing kernel Hilbert spaces (RKHS). They are widely…

Machine Learning · Statistics 2025-06-24 Motonobu Kanagawa , Philipp Hennig , Dino Sejdinovic , Bharath K. Sriperumbudur

A Hilbert space embedding for probability measures has recently been proposed, wherein any probability measure is represented as a mean element in a reproducing kernel Hilbert space (RKHS). Such an embedding has found applications in…

Machine Learning · Statistics 2010-03-04 Bharath K. Sriperumbudur , Kenji Fukumizu , Gert R. G. Lanckriet

This paper establishes error bounds for the convergence of a piecewise linear approximation of the constrained optimal smoothing problem posed in a reproducing kernel Hilbert space (RKHS). This problem can be reformulated as a Bayesian…

Statistics Theory · Mathematics 2025-06-24 Laurence Grammont , François Bachoc , Andrés F. López-Lopera

Many interesting machine learning problems are best posed by considering instances that are distributions, or sample sets drawn from distributions. Previous work devoted to machine learning tasks with distributional inputs has done so…

Machine Learning · Statistics 2021-01-15 Danica J. Sutherland , Junier B. Oliva , Barnabás Póczos , Jeff Schneider

This paper addresses the problem of regression to reconstruct functions, which are observed with superimposed errors at random locations. We address the problem in reproducing kernel Hilbert spaces. It is demonstrated that the estimator,…

Statistics Theory · Mathematics 2021-08-17 Paul Dommel , Alois Pichler

The construction of $r$-nets offers a powerful tool in computational and metric geometry. We focus on high-dimensional spaces and present a new randomized algorithm which efficiently computes approximate $r$-nets with respect to Euclidean…

Computational Geometry · Computer Science 2017-05-09 Georgia Avarikioti , Ioannis Z. Emiris , Loukas Kavouras , Ioannis Psarros

We show in this note that the Sobolev Discrepancy introduced in Mroueh et al in the context of generative adversarial networks, is actually the weighted negative Sobolev norm $||.||_{\dot{H}^{-1}(\nu_q)}$, that is known to linearize the…

Machine Learning · Computer Science 2018-05-17 Youssef Mroueh

Kernel expansions are a topic of considerable interest in machine learning, also because of their relation to the so-called feature maps introduced in machine learning. Properties of the associated basis functions and weights (corresponding…

Machine Learning · Computer Science 2024-10-03 Mauro Bisiacco , Gianluigi Pillonetto

This paper introduces a novel, non-deterministic method for embedding data in low-dimensional Euclidean space based on computing realizations of a Gaussian process depending on the geometry of the data. This type of embedding first appeared…

Machine Learning · Computer Science 2024-03-14 Anna C. Gilbert , Kevin O'Neill

Despite their success, kernel methods suffer from a massive computational cost in practice. In this paper, in lieu of commonly used kernel expansion with respect to $N$ inputs, we develop a novel optimal design maximizing the entropy among…

Machine Learning · Computer Science 2020-02-12 Liang Ding , Rui Tuo , Shahin Shahrampour

Although recovering an Euclidean distance matrix from noisy observations is a common problem in practice, how well this could be done remains largely unknown. To fill in this void, we study a simple distance matrix estimate based upon the…

Machine Learning · Statistics 2014-09-18 Luwan Zhang , Grace Wahba , Ming Yuan