Image de couverture de livre

Geometric Layer-wise Approximation Rates for Deep Networks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Shijun, Shen, Zuowei, Xu, Yuesheng
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Numerical Analysis
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Multigrade Neural Network Approximation
par: Zhang, Shijun, et autres
Publié: (2026)

Deep Neural Network Solutions for Oscillatory Fredholm Integral Equations
par: Jiang, Jie, et autres
Publié: (2024)

Computational Advantages of Multi-Grade Deep Learning: Convergence Analysis and Performance Insights
par: Fang, Ronglong, et autres
Publié: (2025)

Why Shallow Networks Struggle to Approximate and Learn High Frequencies
par: Zhang, Shijun, et autres
Publié: (2023)

On the Dimension-Free Approximation of Deep Neural Networks for Symmetric Korobov Functions
par: Lu, Yulong, et autres
Publié: (2025)

Structured and Balanced Multi-Component and Multi-Layer Neural Networks
par: Zhang, Shijun, et autres
Publié: (2024)

Expressive Power of Deep Networks on Manifolds: Simultaneous Approximation
par: Zhou, Hanfei, et autres
Publié: (2025)

Approximation with SiLU Networks: Constant Depth and Exponential Rates for Basic Operations
par: Ayena, Koffi O.
Publié: (2025)

Approximation Power of Deep Neural Networks: an explanatory mathematical survey
par: Davis, Owen, et autres
Publié: (2022)

Numerical Fragility in Transformers: A Layer-wise Theory for Explaining, Forecasting, and Mitigating Instability
par: Baek, Jinwoo
Publié: (2025)

Higher Order Approximation Rates for ReLU CNNs in Korobov Spaces
par: Li, Yuwen, et autres
Publié: (2025)

Sobolev Approximation of Deep ReLU Networks in Log-Barron Space
par: Song, Changhoon, et autres
Publié: (2026)

Inverse Evolution Layers: Physics-informed Regularizers for Deep Neural Networks
par: Liu, Chaoyu, et autres
Publié: (2023)

A Deep Learning Framework for Multi-Operator Learning: Architectures and Approximation Theory
par: Weihs, Adrien, et autres
Publié: (2025)

ChebNet: Efficient and Stable Constructions of Deep Neural Networks with Rectified Power Units via Chebyshev Approximations
par: Tang, Shanshan, et autres
Publié: (2019)

Error Analysis and Numerical Algorithm for PDE Approximation with Hidden-Layer Concatenated Physics Informed Neural Networks
par: Qian, Yianxia, et autres
Publié: (2024)

Operator SVD with Neural Networks via Nested Low-Rank Approximation
par: Ryu, J. Jon, et autres
Publié: (2024)

Sinusoidal Approximation Theorem for Kolmogorov-Arnold Networks
par: Gleyzer, Sergei, et autres
Publié: (2025)

Expressivity and Approximation Properties of Deep Neural Networks with ReLU$^k$ Activation
par: He, Juncai, et autres
Publié: (2023)

An Efficient Deep Learning Approach for Approximating Parameter-to-Solution Maps of PDEs
par: Lei, Guanhang, et autres
Publié: (2024)

Simultaneous Approximation of the Score Function and Its Derivatives by Deep Neural Networks
par: Yakovlev, Konstantin, et autres
Publié: (2025)

Smoothness Adaptivity in Constant-Depth Neural Networks: Optimal Rates via Smooth Activations
par: Liu, Yuhao, et autres
Publié: (2026)

Maximal Volume Matrix Cross Approximation for Image Compression and Least Squares Solution
par: Allen, Kenneth, et autres
Publié: (2023)

Generative Feature Training of Thin 2-Layer Networks
par: Hertrich, Johannes, et autres
Publié: (2024)

Approximating Matrix Functions with Deep Neural Networks and Transformers
par: Padmanabhan, Rahul, et autres
Publié: (2026)

Conformalized-DeepONet: A Distribution-Free Framework for Uncertainty Quantification in Deep Operator Networks
par: Moya, Christian, et autres
Publié: (2024)

Approximation Rates in Besov Norms and Sample-Complexity of Kolmogorov-Arnold Networks with Residual Connections
par: Kratsios, Anastasis, et autres
Publié: (2025)

Deep Eigenspace Network for Parametric Non-self-adjoint Eigenvalue Problems
par: Li, H., et autres
Publié: (2025)

Sharp Lower Bounds for Linearized ReLU^k Approximation on the Sphere
par: Mao, Tong, et autres
Publié: (2025)

Convergence of Stochastic Gradient Methods for Wide Two-Layer Physics-Informed Neural Networks
par: Jin, Bangti, et autres
Publié: (2025)

Deep Network Trainability via Persistent Subspace Orthogonality
par: Massucco, Alex, et autres
Publié: (2025)

On the Role of Initialization on the Implicit Bias in Deep Linear Networks
par: Gruber, Oria, et autres
Publié: (2024)

Deep NURBS -- Admissible Physics-informed Neural Networks
par: Saidaoui, Hamed, et autres
Publié: (2022)

Lattice-based Deep Neural Networks: Regularity and Tailored Regularization
par: Keller, Alexander, et autres
Publié: (2026)

Physics-informed Discretization-independent Deep Compositional Operator Network
par: Zhong, Weiheng, et autres
Publié: (2024)

Approximation properties of neural ODEs
par: De Marinis, Arturo, et autres
Publié: (2025)

Data-Driven Approximation of Binary-State Network Reliability Function: Algorithm Selection and Reliability Thresholds for Large-Scale Systems
par: Yeh, Wei-Chang
Publié: (2025)

Approximation Rates in Fréchet Metrics: Barron Spaces, Paley-Wiener Spaces, and Fourier Multipliers
par: Abdeljawad, Ahmed, et autres
Publié: (2024)

Efficient Transformer-Inspired Variants of Physics-Informed Deep Operator Networks
par: Wei, Zhi-Feng, et autres
Publié: (2025)

PirateNets: Physics-informed Deep Learning with Residual Adaptive Networks
par: Wang, Sifan, et autres
Publié: (2024)