Universal Approximation Theorem for Equivariant Maps by Group CNNs

Wataru Kumagai, Akiyoshi Sannai

Type: Preprint

Publication Date: 2020-01-01

Citations: 6

DOI: https://doi.org/10.48550/arxiv.2012.13882

View Publication

Locations

arXiv (Cornell University) - View - PDF
DataCite API - View

Similar Works

Action	Title	Year	Authors
+ PDF Chat	Decomposition of Equivariant Maps via Invariant Maps: Application to Universal Approximation under Symmetry	2024	Akiyoshi Sannai Yuuki Takai Matthieu Cordonnier
+	A General Theory of Equivariant CNNs on Homogeneous Spaces	2018	Taco Cohen Mario Geiger Maurice Weiler
+ PDF Chat	Exploiting Learned Symmetries in Group Equivariant Convolutions	2021	Attila Lengyel Jan van Gemert
+	Exploiting Learned Symmetries in Group Equivariant Convolutions	2021	Attila Lengyel Jan C. van Gemert
+	Improved Generalization Bounds of Group Invariant / Equivariant Deep Networks via Quotient Feature Spaces	2019	Akiyoshi Sannai Masaaki Imaizumi Makoto Kawano
+	Almost Equivariance via Lie Algebra Convolutions	2023	Daniel McNeela
+	Universal Equivariant Multilayer Perceptrons	2020	Siamak Ravanbakhsh
+	Universal Equivariant Multilayer Perceptrons	2020	Siamak Ravanbakhsh
+	Lie Group Decompositions for Equivariant Neural Networks	2023	Mircea Mironenco Patrick Forré
+	Theoretical Aspects of Group Equivariant Neural Networks	2020	Carlos Esteves
+	A tradeoff between universality of equivariant models and learnability of symmetries	2022	Vasco Portilheiro
+	A Characterization Theorem for Equivariant Networks with Point-wise Activations	2024	Marco Pacini Xiaowen Dong Bruno Lepri Gabriele Santin
+	Equivariant neural networks and equivarification	2019	Erkao Bao Linqi Song
+	What is... an Equivariant Neural Network?	2023	Lek‐Heng Lim Bradley J. Nelson
+	Learning Equivariances and Partial Equivariances from Data	2021	David W. Romero Suhas Lohit
+	Universal approximations of permutation invariant/equivariant functions by deep neural networks	2019	Akiyoshi Sannai Yuuki Takai Matthieu Cordonnier
+	Investigating how ReLU-networks encode symmetries	2023	Georg Bökman Fredrik Kahl
+ PDF Chat	Constructive Universal Approximation Theorems for Deep Joint-Equivariant Networks by Schur's Lemma	2024	Sho Sonoda Yuka Hashimoto Isao Ishikawa Masahiro Ikeda
+ PDF Chat	Stability Analysis of Equivariant Convolutional Representations Through The Lens of Equivariant Multi-layered CKNs	2024	Soutrik Roy Chowdhury
+ PDF Chat	Equivariant neural networks and piecewise linear representation theory	2024	Joel Gibson Daniel Tubbenhauer Geordie Williamson

Works That Cite This (4)

Action	Title	Year	Authors
+ PDF Chat	Approximation properties of deep ReLU CNNs	2022	Juncai He Lin Li Jinchao Xu
+	On Non-Linear operators for Geometric Deep Learning	2022	Grégoire Sergeant-Perthuis Jakob Maier Joan Bruna Edouard Oyallon
+ PDF Chat	fKAN: Fractional Kolmogorov-Arnold Networks with trainable Jacobi basis functions	2025	Alireza Afzal Aghaei
+	Ghosts in Neural Networks: Existence, Structure and Role of Infinite-Dimensional Null Space	2021	Sho Sonoda Isao Ishikawa Masahiro Ikeda

Works Cited by This (16)

Action	Title	Year	Authors
+	Group Actions on Manifolds	1985	Reinhard Schultz
+	A functional analysis point of view on compactness theorems in function spaces	2018	Mateusz Krukowski
+	On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups	2018	Risi Kondor Shubhendu Trivedi
+	Universal approximations of invariant maps by neural networks	2018	Dmitry Yarotsky
+	Universal approximations of permutation invariant/equivariant functions by deep neural networks	2019	Akiyoshi Sannai Yuuki Takai Matthieu Cordonnier
+	Poincaré Embeddings for Learning Hierarchical Representations	2017	Maximilian Nickel Douwe Kiela
+	On Universal Approximation by Neural Networks with Uniform Guarantees on Approximation of Infinite Dimensional Maps	2019	William H. Guss Ruslan Salakhutdinov
+	A Simple Proof of the Universality of Invariant/Equivariant Graph Neural Networks	2019	Takanori Maehara Hoang Nt
+	Convolutional Conditional Neural Processes	2019	Jonathan Gordon Wessel P. Bruinsma Andrew Y. K. Foong James Requeima Yann Dubois Richard E. Turner
+ PDF Chat	Equivalence of approximation by convolutional neural networks and fully-connected networks	2019	Philipp Petersen Felix Voigtlaender