Imagen de Portada

Numerical Approximation Capacity of Neural Networks with Bounded Parameters: Do Limits Exist, and How Can They Be Measured?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Li, Yu, Tengchao, Yong, Heng
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Approximation Bounds for Recurrent Neural Networks with Application to Regression
por: Jiao, Yuling, et al.
Publicado: (2024)

Do Neural Scaling Laws Exist on Graph Self-Supervised Learning?
por: Ma, Qian, et al.
Publicado: (2024)

Upper Approximation Bounds for Neural Oscillators
por: Huang, Zifeng, et al.
Publicado: (2025)

DeePoly: A High-Order Accuracy Scientific Machine Learning Framework for Function Approximation and Solving PDEs
por: Liu, Li, et al.
Publicado: (2025)

On the Generalization and Approximation Capacities of Neural Controlled Differential Equations
por: Bleistein, Linus, et al.
Publicado: (2023)

How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective
por: Zhang, Qiaozhe, et al.
Publicado: (2023)

How Accurately Can a Gaussian Approximate Stochastic Approximation Iterates?
por: Haque, Shaan Ul, et al.
Publicado: (2026)

Implicit Hypersurface Approximation Capacity in Deep ReLU Networks
por: Vallin, Jonatan, et al.
Publicado: (2024)

Approximation Bounds for Transformer Networks with Application to Regression
por: Jiao, Yuling, et al.
Publicado: (2025)

Compressing Neural Networks Using Tensor Networks with Exponentially Fewer Variational Parameters
por: Qing, Yong, et al.
Publicado: (2023)

Symmetry in Neural Network Parameter Spaces
por: Zhao, Bo, et al.
Publicado: (2025)

Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations
por: Sartor, Davide, et al.
Publicado: (2025)

Guaranteed Approximation Bounds for Mixed-Precision Neural Operators
por: Tu, Renbo, et al.
Publicado: (2023)

Rethinking the Capacity of Graph Neural Networks for Branching Strategy
por: Chen, Ziang, et al.
Publicado: (2024)

PAC-Bayesian Generalization Bounds for Graph Convolutional Networks on Inductive Node Classification
por: Tang, Huayi, et al.
Publicado: (2025)

Fast and Slow Gradient Approximation for Binary Neural Network Optimization
por: Chen, Xinquan, et al.
Publicado: (2024)

Parameter-Adaptive Approximate MPC: Tuning Neural-Network Controllers without Retraining
por: Hose, Henrik, et al.
Publicado: (2024)

BI-EqNO: Generalized Approximate Bayesian Inference with an Equivariant Neural Operator Framework
por: Zhou, Xu-Hui, et al.
Publicado: (2024)

Expectation Error Bounds for Transfer Learning in Linear Regression and Linear Neural Networks
por: Liu, Meitong, et al.
Publicado: (2026)

Auditing Near-Optimal Policies Can Be Exponentially Hard: Conditional Query Lower Bounds via Occupancy Rashomon Capacity
por: Shihab, Ibne Farabi, et al.
Publicado: (2026)

VAEs and GANs: Implicitly Approximating Complex Distributions with Simple Base Distributions and Deep Neural Networks -- Principles, Necessity, and Limitations
por: Wei, Yuan-Hao
Publicado: (2025)

Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks
por: Yang, Zhuobin, et al.
Publicado: (2026)

Multigrade Neural Network Approximation
por: Zhang, Shijun, et al.
Publicado: (2026)

How Do the Architecture and Optimizer Affect Representation Learning? On the Training Dynamics of Representations in Deep Neural Networks
por: Sharon, Yuval, et al.
Publicado: (2024)

Breaking the Correlation Plateau: On the Optimization and Capacity Limits of Attention-Based Regressors
por: Yan, Jingquan, et al.
Publicado: (2026)

Neural Networks With Dense Weights Are Not Universal Approximators
por: Rauchwerger, Levi, et al.
Publicado: (2026)

Neural Network Training with Approximate Logarithmic Computations
por: Sanyal, Arnab, et al.
Publicado: (2019)

Differential Equation Scaling Limits of Shaped and Unshaped Neural Networks
por: Li, Mufan Bill, et al.
Publicado: (2023)

The Influence of the Memory Capacity of Neural DDEs on the Universal Approximation Property
por: Kuehn, Christian, et al.
Publicado: (2025)

Generalization and Risk Bounds for Recurrent Neural Networks
por: Cheng, Xuewei, et al.
Publicado: (2024)

Bounded Graph Clustering with Graph Neural Networks
por: Neocosmos, Kibidi, et al.
Publicado: (2025)

Generalization Bounds for Rank-sparse Neural Networks
por: Ledent, Antoine, et al.
Publicado: (2025)

Polysemanticity and Capacity in Neural Networks
por: Scherlis, Adam, et al.
Publicado: (2022)

Forgetting Similar Samples: Can Machine Unlearning Do it Better?
por: Xu, Heng, et al.
Publicado: (2026)

Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks?
por: Nimase, Ojas, et al.
Publicado: (2026)

Approximating Numerical Fluxes Using Fourier Neural Operators for Hyperbolic Conservation Laws
por: Kim, Taeyoung, et al.
Publicado: (2024)

Deep Neural Networks are Adaptive to Function Regularity and Data Distribution in Approximation and Estimation
por: Liu, Hao, et al.
Publicado: (2024)

Towards Sharper Risk Bounds for Minimax Problems
por: Zhu, Bowei, et al.
Publicado: (2024)

Error Analysis and Numerical Algorithm for PDE Approximation with Hidden-Layer Concatenated Physics Informed Neural Networks
por: Qian, Yianxia, et al.
Publicado: (2024)

Neural Network Approximation: A View from Polytope Decomposition
por: Li, ZeYu, et al.
Publicado: (2026)