English
Related papers

Related papers: Learning convolution operators on compact Abelian …

200 papers

In the context of kernel optimization, we prove a result that yields new factorizations and realizations. Our initial context is that of general positive operator-valued kernels. We further present implications for Hilbert space-valued…

Operator Algebras · Mathematics 2024-10-14 Palle E. T. Jorgensen , James Tian

Regularization is used to find a solution that both fits the data and is sufficiently smooth, and thereby is very effective for designing and refining learning algorithms. But the influence of its exponent remains poorly understood. In…

Machine Learning · Statistics 2016-12-15 Julien Audiffren , Hachem Kadri

We propose a framework for transfer learning of discount curves across different fixed-income product classes. Motivated by challenges in estimating discount curves from sparse or noisy data, we extend kernel ridge regression (KR) to a…

Machine Learning · Statistics 2026-01-14 Nicolas Camenzind , Damir Filipovic

In this paper, an online learning algorithm is proposed as sequential stochastic approximation of a regularization path converging to the regression function in reproducing kernel Hilbert spaces (RKHSs). We show that it is possible to…

Probability · Mathematics 2013-01-23 Pierre Tarrès , Yuan Yao

Adversarial training and data augmentation with noise are widely adopted techniques to enhance the performance of neural networks. This paper investigates adversarial training and data augmentation with noise in the context of regularized…

Machine Learning · Statistics 2023-04-20 Teng Zhang , Kang Li

There has been growing recent interest in probabilistic interpretations of kernel-based methods as well as learning in Banach spaces. The absence of a useful Lebesgue measure on an infinite-dimensional reproducing kernel Hilbert space is a…

Machine Learning · Statistics 2014-03-14 Irina Holmes , Ambar Sengupta

Invariance and equivariance to geometrical transformations have proven to be very useful inductive biases when training (convolutional) neural network models, especially in the low-data regime. Much work has focused on the case where the…

Machine Learning · Computer Science 2024-07-11 Mircea Mironenco , Patrick Forré

Regularity theorems \`a la Avellaneda-Lin are an indispensable part of the modern quantitative theory of stochastic homogenization. While interior regularity results for random elliptic operators have been available for a while, on general…

Analysis of PDEs · Mathematics 2026-04-02 Peter Bella , Julian Fischer , Marc Josien , Claudia Raithel

Distributionally robust optimization (DRO) has attracted attention in machine learning due to its connections to regularization, generalization, and robustness. Existing work has considered uncertainty sets based on phi-divergences and…

Machine Learning · Computer Science 2019-05-28 Matthew Staib , Stefanie Jegelka

Motivated by the study of H\"ormander's sums-of-squares operators and their generalizations, we define the convolution algebra of transverse distributions associated to a singular foliation. We prove that this algebra is represented as…

Analysis of PDEs · Mathematics 2020-04-20 Iakovos Androulidakis , Omar Mohsen , Robert Yuncken

Strictly proper kernel scores are well-known tool in probabilistic forecasting, while characteristic kernels have been extensively investigated in the machine learning literature. We first show that both notions coincide, so that insights…

Functional Analysis · Mathematics 2017-12-15 Ingo Steinwart , Johanna F. Ziegel

We adress the problem of Laplace deconvolution with random noise in a regression framework. The time set is not considered to be fixed, but grows with the number of observation points. Moreover, the convolution kernel is unknown, and…

Statistics Theory · Mathematics 2013-04-05 Thomas Vareschi

In this paper we investigate the problem of estimating the regression function in models with correlated observations. The data is obtained from several experimental units each of them forms a time series. We propose a new estimator based…

Statistics Theory · Mathematics 2019-06-13 Djihad Benelmadani , Karim Benhenni , Sana Louhichi

To study operator algebras with symmetries in a wide sense we introduce a notion of {\em relative convolution operators} induced by a Lie algebra. Relative convolutions recover many important classes of operators, which have been already…

funct-an · Mathematics 2008-02-03 Vladimir V. Kisil

This expository article presents the approach to statistical machine learning based on reproducing kernel Hilbert spaces. The basic framework is introduced for scalar-valued learning and then extended to operator learning. Finally, learning…

Machine Learning · Computer Science 2025-09-24 Lorenzo Rosasco

Kernel methods, being supported by a well-developed theory and coming with efficient algorithms, are among the most popular and successful machine learning techniques. From a mathematical point of view, these methods rest on the concept of…

Machine Learning · Statistics 2023-03-20 Christian Fiedler , Michael Herty , Michael Rom , Chiara Segala , Sebastian Trimpe

The convolution operator is the fundamental building block of modern convolutional neural networks (CNNs), owing to its simplicity, translational equivariance, and efficient implementation. However, its structure as a fixed, linear,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Simone Cammarasana

Regularization is a well recognized powerful strategy to improve the performance of a learning machine and $l^q$ regularization schemes with $0<q<\infty$ are central in use. It is known that different $q$ leads to different properties of…

Machine Learning · Computer Science 2014-09-26 Shaobo Lin , Jinshan Zeng , Jian Fang , Zongben Xu

Reproducing kernel Hilbert spaces are elucidated without assuming prior familiarity with Hilbert spaces. Compared with extant pedagogic material, greater care is placed on motivating the definition of reproducing kernel Hilbert spaces and…

History and Overview · Mathematics 2015-11-06 Jonathan H. Manton , Pierre-Olivier Amblard

We develop a variational framework to understand the properties of the functions learned by neural networks fit to data. We propose and study a family of continuous-domain linear inverse problems with total variation-like regularization in…

Machine Learning · Statistics 2021-02-15 Rahul Parhi , Robert D. Nowak