English
Related papers

Related papers: Generalising maximum mean discrepancy: kernelised …

200 papers

Information divergences are commonly used to measure the dissimilarity of two elements on a statistical manifold. Differentiable manifolds endowed with different divergences may possess different geometric properties, which can result in…

Signal Processing · Electrical Eng. & Systems 2021-08-17 Xiaoqiang Hua , Yusuke Ono , Linyu Peng , Yongqiang Cheng , Hongqiang Wang

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 this paper, we focus on subspace-based learning problems, where data elements are linear subspaces instead of vectors. To handle this kind of data, Grassmann kernels were proposed to measure the space structure and used with classifiers,…

Machine Learning · Computer Science 2018-06-19 Junyuan Hong , Huanhuan Chen , Feng Lin

In this note we study some basic properties of general fractional derivatives induced by weighted Bergman kernels. As an application we demonstrate a method for generating pre-images of analytic functions under weighted Bergman projections.…

Complex Variables · Mathematics 2018-10-05 Antti Perälä

Fisher's linear discriminant analysis is a classical method for classification, yet it is limited to capturing linear features only. Kernel discriminant analysis as an extension is known to successfully alleviate the limitation through a…

Machine Learning · Statistics 2022-07-29 Jiae Kim , Yoonkyung Lee , Zhiyu Liang

Divergence functions are interesting discrepancy measures. Even though they are not true distances, we can use them to measure how separated two points are. Curiously enough, when they are applied to random variables, they lead to a notion…

Statistics Theory · Mathematics 2018-09-21 Henryk Gzyl

Hyperspectral imaging is a powerful technology that is plagued by large dimensionality. Herein, we explore a way to combat that hindrance via non-contiguous and contiguous (simpler to realize sensor) band grouping for dimensionality…

Image and Video Processing · Electrical Eng. & Systems 2019-05-31 Muhammad Aminul Islam , Derek T. Anderson , John E. Ball , Nicolas H. Younan

Many problems in machine learning write as the minimization of a sum of individual loss functions over the training examples. These functions are usually differentiable but, in some cases, their gradients are not Lipschitz continuous, which…

Optimization and Control · Mathematics 2024-04-29 S. Chraibi , F. Iutzeler , J. Malick , A. Rogozin

The aim of the present paper is three folds. For a reproducing kernel Hilbert space $\mathcal{A}$ (R.K.H.S) and a $\sigma-$finite measure space $(M_{1},d\mu_{1})$ for which the corresponding $L^{2}-$space is a separable Hilbert space, we…

Functional Analysis · Mathematics 2019-12-13 Nour eddine Askour , Mohamed Bouaouid

The success of kernel methods has initiated the design of novel positive semidefinite functions, in particular for structured data. A leading design paradigm for this is the convolution kernel, which decomposes structured objects into their…

Machine Learning · Computer Science 2017-02-01 Nils M. Kriege , Pierre-Louis Giscard , Richard C. Wilson

Semi-inner-products in the sense of Lumer are extended to convex functionals. This yields a Hilbert-space like structure to convex functionals in Banach spaces. In particular, a general expression for semi-inner-products with respect to one…

Numerical Analysis · Mathematics 2015-11-17 Guy Gilboa

We study the convergence of Bernstein type operators leading to two results. The first: The kernel $K_n$ of the Bernstein-Durrmeyer operator at each point $x \in (0, 1)$ $\unicode{x2013}$ that is $K_n(x, t) dt$ $\unicode{x2013}$ once…

Classical Analysis and ODEs · Mathematics 2023-12-05 Mohammed Taariq Mowzer

We show that the Bregman divergence provides a rich framework to estimate unnormalized statistical models for continuous or discrete random variables, that is, models which do not integrate or sum to one, respectively. We prove that recent…

Machine Learning · Computer Science 2012-02-20 Michael Gutmann , Jun-ichiro Hirayama

Estimating Kullback Leibler (KL) divergence from samples of two distributions is essential in many machine learning problems. Variational methods using neural network discriminator have been proposed to achieve this task in a scalable…

Machine Learning · Computer Science 2021-10-01 Sandesh Ghimire , Aria Masoomi , Jennifer Dy

We introduce a divergence measure between data distributions based on operators in reproducing kernel Hilbert spaces defined by kernels. The empirical estimator of the divergence is computed using the eigenvalues of positive definite Gram…

Machine Learning · Computer Science 2023-05-31 Jhoan Keider Hoyos Osorio , Oscar Skean , Austin J. Brockmeier , Luis Gonzalo Sanchez Giraldo

Deep Generative Models (DGMs), including Energy-Based Models (EBMs) and Score-based Generative Models (SGMs), have advanced high-fidelity data generation and complex continuous distribution approximation. However, their application in…

Machine Learning · Computer Science 2024-10-03 Yangming Li , Chieh-Hsin Lai , Carola-Bibiane Schönlieb , Yuki Mitsufuji , Stefano Ermon

We present a Bayesian model for pairwise nonlinear registration of functional data. We use the Riemannian geometry of the space of warping functions to define appropriate prior distributions and sample from the posterior using importance…

Methodology · Statistics 2017-02-07 Sebastian Kurtek

We consider the problem of learning a set from random samples. We show how relevant geometric and topological properties of a set can be studied analytically using concepts from the theory of reproducing kernel Hilbert spaces. A new kind of…

Machine Learning · Statistics 2014-11-26 Ernesto De Vito , Lorenzo Rosasco , Alessandro Toigo

Metric and kernel learning are important in several machine learning applications. However, most existing metric learning algorithms are limited to learning metrics over low-dimensional data, while existing kernel learning algorithms are…

Machine Learning · Computer Science 2009-11-02 Prateek Jain , Brian Kulis , Jason V. Davis , Inderjit S. Dhillon

Spectral clustering and diffusion maps are celebrated dimensionality reduction algorithms built on eigen-elements related to the diffusive structure of the data. The core of these procedures is the approximation of a Laplacian through a…

Machine Learning · Statistics 2023-02-15 Loucas Pillaud-Vivien , Francis Bach