paper-with-me

홈 › Papers

Learning convolution operators on compact Abelian groups

2025-01-09 · Emilia Magnani, Ernesto de Vito, Philipp Hennig, Lorenzo Rosasco

We consider the problem of learning convolution operators associated to compact Abelian groups. We study a regularization-based approach and provide corresponding learning guarantees under natural regularity conditions on the convolution kernel. More precisely, we assume the convolution kernel is a function in a translation invariant Hilbert space and analyze a natural ridge regression (RR) estimator. Building on existing results for RR, we characterize the accuracy of the estimator in terms of finite sample bounds. Interestingly, regularity assumptions which are classical in the analysis of RR, have a novel and natural interpretation in terms of space/frequency localization. Theoretical results are illustrated by numerical simulations.

📄 PDF Abstract BibTeX arXiv:2501.05279

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Lie Group Decompositions for Equivariant Neural Networks

2023-10-17 · Mircea Mironenco, Patrick Forré

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 t…

Scattering Networks on Noncommutative Finite Groups

2025-05-27 · Maria Teresa Arias, Davide Barbieri, Eugenio Hernández

Scattering Networks were initially designed to elucidate the behavior of early layers in Convolutional Neural Networks (CNNs) over Euclidean spaces and are grounded in wavelets. In this work, we introduce a scattering tr…

Digital implementations of deep feature extractors are intrinsically informative

2025-02-20 · Max Getter

Rapid information (energy) propagation in deep feature extractors is crucial to balance computational complexity versus expressiveness as a representation of the input. We prove an upper bound for the speed of energy pro…

Towards a topological-geometrical theory of group equivariant non-expansive operators for data analysis and machine learning

2018-12-31 · Mattia G. Bergomi, Patrizio Frosini, Daniela Giorgi, Nicola Quercioli

The aim of this paper is to provide a general mathematical framework for group equivariance in the machine learning context. The framework builds on a synergy between persistent homology and the theory of group actions. …

BIG-bench Machine LearningMetric Learning

A general unified framework for interval pairwise comparison matrices

2017-11-26 · Bice Cavallo, Matteo Brunelli

Interval Pairwise Comparison Matrices have been widely used to account for uncertain statements concerning the preferences of decision makers. Several approaches have been proposed in the literature, such as multiplicati…