Imagen de Portada

Neural Networks With Dense Weights Are Not Universal Approximators

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Rauchwerger, Levi, Jegelka, Stefanie, Levie, Ron
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs
por: Rauchwerger, Levi, et al.
Publicado: (2024)

A Note on Graphon-Signal Analysis of Graph Neural Networks
por: Rauchwerger, Levi, et al.
Publicado: (2025)

Survey on Generalization Theory for Graph Neural Networks
por: Vasileiou, Antonis, et al.
Publicado: (2025)

A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation
por: Amran, Ofek, et al.
Publicado: (2026)

Higher-Order Graphon Neural Networks: Approximation and Cut Distance
por: Herbst, Daniel, et al.
Publicado: (2025)

PieClam: A Universal Graph Autoencoder Based on Overlapping Inclusive and Exclusive Communities
por: Zilberg, Daniel, et al.
Publicado: (2024)

Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks
por: Lin, Ya-Wei Eileen, et al.
Publicado: (2025)

Generalization Bounds for Message Passing Networks on Mixture of Graphons
por: Maskey, Sohir, et al.
Publicado: (2024)

Learning to Approximate Uniform Facility Location via Graph Neural Networks
por: Qian, Chendi, et al.
Publicado: (2026)

Counting Substructures with Higher-Order Graph Neural Networks: Possibility and Impossibility Results
por: Tahmasebi, Behrooz, et al.
Publicado: (2020)

Are Graph Neural Networks Optimal Approximation Algorithms?
por: Yau, Morris, et al.
Publicado: (2023)

Sample Complexity Bounds for Estimating Probability Divergences under Invariances
por: Tahmasebi, Behrooz, et al.
Publicado: (2023)

The Exact Sample Complexity Gain from Invariances for Kernel Regression
por: Tahmasebi, Behrooz, et al.
Publicado: (2023)

Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables
por: Nagar, Eden, et al.
Publicado: (2026)

Equivariant Machine Learning on Graphs with Nonlinear Spectral Filters
por: Lin, Ya-Wei Eileen, et al.
Publicado: (2024)

Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models
por: Putterman, Theo, et al.
Publicado: (2024)

A Universal Class of Sharpness-Aware Minimization Algorithms
por: Tahmasebi, Behrooz, et al.
Publicado: (2024)

Efficient Learning on Large Graphs using a Densifying Regularity Lemma
por: Kouchly, Jonathan, et al.
Publicado: (2025)

A Poincaré Inequality and Consistency Results for Signal Sampling on Large Graphs
por: Le, Thien, et al.
Publicado: (2023)

Future Directions in the Theory of Graph Machine Learning
por: Morris, Christopher, et al.
Publicado: (2024)

Any-Subgroup Equivariant Networks via Symmetry Breaking
por: Goel, Abhinav, et al.
Publicado: (2026)

Dataset of Pathloss and ToA Radio Maps With Localization Application
por: Yapar, Çağkan, et al.
Publicado: (2022)

Finite-Dimensional Gaussian Approximation for Deep Neural Networks: Universality in Random Weights
por: Balasubramanian, Krishnakumar, et al.
Publicado: (2025)

Learning on Large Graphs using Intersecting Communities
por: Finkelshtein, Ben, et al.
Publicado: (2024)

Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models
por: Finkelshtein, Ben, et al.
Publicado: (2025)

Neural Networks Trained by Weight Permutation are Universal Approximators
por: Cai, Yongqiang, et al.
Publicado: (2024)

Learning Efficient Positional Encodings with Graph Neural Networks
por: Kanatsoulis, Charilaos I., et al.
Publicado: (2025)

The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof
por: Lim, Derek, et al.
Publicado: (2024)

On the Emergence of Position Bias in Transformers
por: Wu, Xinyi, et al.
Publicado: (2025)

ReasonCACHE: Teaching LLMs To Reason Without Weight Updates
por: Gupta, Sharut, et al.
Publicado: (2026)

Training Deep Morphological Neural Networks as Universal Approximators
por: Fotopoulos, Konstantinos, et al.
Publicado: (2025)

Joint Surrogate Learning of Objectives, Constraints, and Sensitivities for Efficient Multi-objective Optimization of Neural Dynamical Systems
por: Gressmann, Frithjof, et al.
Publicado: (2026)

DiBA: Diagonal and Binary Matrix Approximation for Neural Network Weight Compression
por: Ono, Nobutaka
Publicado: (2026)

A projection-based framework for gradient-free and parallel learning
por: Bergmeister, Andreas, et al.
Publicado: (2025)

LieAugmenter: Equivariant Learning by Discovering Symmetries with Learnable Augmentations
por: Santos-Escriche, Eduardo, et al.
Publicado: (2025)

Near-Optimal Algorithms for Group Distributionally Robust Optimization and Beyond
por: Soma, Tasuku, et al.
Publicado: (2022)

Learning with Exact Invariances in Polynomial Time
por: Soleymani, Ashkan, et al.
Publicado: (2025)

Geometric Algorithms for Neural Combinatorial Optimization with Constraints
por: Karalias, Nikolaos, et al.
Publicado: (2025)

Canonicalizing Multimodal Contrastive Representation Learning
por: Gupta, Sharut, et al.
Publicado: (2026)

A Canonicalization Perspective on Invariant and Equivariant Learning
por: Ma, George, et al.
Publicado: (2024)