English
Related papers

Related papers: Neurally-plausible radial basis kernels using dist…

200 papers

Modern Bayesian optimization and adaptive sampling methods increasingly rely on nonlinear parametric models, yet theoretical guarantees for such models under adaptive data collection remain limited. Existing analyses largely focus on…

Machine Learning · Statistics 2026-05-14 Rafael Oliveira

Characterizing the function spaces corresponding to neural networks can provide a way to understand their properties. In this paper we discuss how the theory of reproducing kernel Banach spaces can be used to tackle this challenge. In…

Machine Learning · Statistics 2021-10-27 Francesca Bartolucci , Ernesto De Vito , Lorenzo Rosasco , Stefano Vigogna

Spatial networks are networks whose graph topology is constrained by their embedded spatial space. Understanding the coupled spatial-graph properties is crucial for extracting powerful representations from spatial networks. Therefore,…

Machine Learning · Computer Science 2024-01-11 Zheng Zhang , Sirui Li , Jingcheng Zhou , Junxiang Wang , Abhinav Angirekula , Allen Zhang , Liang Zhao

We describe a method to perform functional operations on probability distributions of random variables. The method uses reproducing kernel Hilbert space representations of probability distributions, and it is applicable to all operations…

Machine Learning · Statistics 2016-09-14 Bernhard Schölkopf , Krikamol Muandet , Kenji Fukumizu , Jonas Peters

Conceptual and mathematical models of neurons have lagged behind empirical understanding for decades. Here we extend previous work in modeling biological systems with fully scale-independent quantum information-theoretic tools to develop a…

Neurons and Cognition · Quantitative Biology 2022-07-21 Chris Fields , James F. Glazebrook , Michael Levin

An overview of computational methods to describe high-dimensional potential energy surfaces suitable for atomistic simulations is given. Particular emphasis is put on accuracy, computability, transferability and extensibility of the methods…

Chemical Physics · Physics 2020-07-08 Oliver T. Unke , Debasish Koner , Sarbani Patra , Silvan Käser , Markus Meuwly

This work is motivated by the frequent occurrence of boundary value problems with various boundary conditions in the modeling of some problems in engineering and physical science. Here we propose a new technique to force the positive…

Numerical Analysis · Mathematics 2019-06-19 Babak Azarnavid , Mohammad Nabati , Mahdi Emamjome , Kourosh Parand

Proximity Distribution Kernel is an effective method for bag-of-featues based image representation. In this paper, we investigate the soft assignment of visual words to image features for proximity distribution. Visual word contribution…

Computer Vision and Pattern Recognition · Computer Science 2014-06-03 Quanquan Wang , Yongping Li

Generative models, such as large language models and text-to-image diffusion models, produce relevant information when presented a query. Different models may produce different information when presented the same query. As the landscape of…

Machine Learning · Computer Science 2025-01-20 Aranyak Acharyya , Michael W. Trosset , Carey E. Priebe , Hayden S. Helm

Neural Radiance Fields (NeRFs) are a very recent and very popular approach for the problems of novel view synthesis and 3D reconstruction. A popular scene representation used by NeRFs is to combine a uniform, voxel-based subdivision of the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Jonas Kulhanek , Torsten Sattler

We provide the first mathematically complete derivation of the Nystr\"om method for low-rank approximation of indefinite kernels and propose an efficient method for finding an approximate eigendecomposition of such kernel matrices. Building…

Machine Learning · Statistics 2019-06-03 Dino Oglic , Thomas Gärtner

We propose simple nonparametric estimators for mediated and time-varying dose response curves based on kernel ridge regression. By embedding Pearl's mediation formula and Robins' g-formula with kernels, we allow treatments, mediators, and…

Methodology · Statistics 2025-03-18 Rahul Singh , Liyuan Xu , Arthur Gretton

Implicit neural representations (INRs) have arisen as useful methods for representing signals on Euclidean domains. By parameterizing an image as a multilayer perceptron (MLP) on Euclidean space, INRs effectively represent signals in a way…

Signal Processing · Electrical Eng. & Systems 2023-10-03 T. Mitchell Roddenberry , Vishwanath Saragadam , Maarten V. de Hoop , Richard G. Baraniuk

In this paper we solve support vector machines in reproducing kernel Banach spaces with reproducing kernels defined on nonsymmetric domains instead of the traditional methods in reproducing kernel Hilbert spaces. Using the orthogonality of…

Machine Learning · Statistics 2015-01-16 Gregory E. Fasshauer , Fred J. Hickernell , Qi Ye

We propose a novel approach for pixel classification in hyperspectral images, leveraging on both the spatial and spectral information in the data. The introduced method relies on a recently proposed framework for learning on distributions…

Computer Vision and Pattern Recognition · Computer Science 2016-05-31 Gianni Franchi , Jesus Angulo , Dino Sejdinovic

We address the problem of approximating parametric Fourier imaging problems via interpolation/ extrapolation algorithms that impose smoothing constraints across contiguous values of the parameter. Previous works already proved that…

Numerical Analysis · Mathematics 2025-05-21 Anna Volpara , Alessandro Lupoli , Emma Perracchione

We provide explicit commutative sequence space representations for classical function and distribution spaces on the real half-line. This is done by evaluating at the Fourier transforms of the elements of an orthonormal wavelet basis.

Functional Analysis · Mathematics 2022-08-08 Andreas Debrouwere , Lenny Neyt , Jasson Vindas

The necessary and sufficient conditions for existence of a generalized representer theorem are presented for learning Hilbert space-valued functions. Representer theorems involving explicit basis functions and Reproducing Kernels are a…

Machine Learning · Computer Science 2018-09-21 Sanket Diwale , Colin Jones

This paper proposes a novel beamforming framework in the reproducing kernel domain, derived from a unified interpretation of directional response as spatial differentiation of the sound field. By representing directional response using…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-03 Takahiro Iwami , Naohisa Inoue , Akira Omoto

In this paper, the flexibility, versatility and predictive power of kernel regression are combined with now lavishly available network data to create regression models with even greater predictive performances. Building from previous work…

Machine Learning · Statistics 2020-11-05 E. Pei , E. Fokoué