Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss
Fuente:
arXiv
Saved in:
| Main Authors: | Yang, Yahong, He, Juncai |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Deep Neural Networks with General Activations: Super-Convergence in Sobolev Norms
by: Yang, Yahong, et al.
Published: (2025)
by: Yang, Yahong, et al.
Published: (2025)
Deep Neural Networks and Finite Elements of Any Order on Arbitrary Dimensions
by: He, Juncai, et al.
Published: (2023)
by: He, Juncai, et al.
Published: (2023)
Towards regularized learning from functional data with covariate shift
by: Holzleitner, Markus, et al.
Published: (2026)
by: Holzleitner, Markus, et al.
Published: (2026)
Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations
by: Chen, Shuang, et al.
Published: (2026)
by: Chen, Shuang, et al.
Published: (2026)
Why the noise model matters: A performance gap in learned regularization
by: Banert, Sebastian, et al.
Published: (2025)
by: Banert, Sebastian, et al.
Published: (2025)
DeepONet for Solving Nonlinear Partial Differential Equations with Physics-Informed Training
by: Yang, Yahong
Published: (2024)
by: Yang, Yahong
Published: (2024)
Pseudo-Differential Neural Operator: Generalized Fourier Neural Operator for Learning Solution Operators of Partial Differential Equations
by: Shin, Jin Young, et al.
Published: (2022)
by: Shin, Jin Young, et al.
Published: (2022)
Designing Preconditioners for SGD: Local Conditioning, Noise Floors, and Basin Stability
by: Scott, Mitchell, et al.
Published: (2025)
by: Scott, Mitchell, et al.
Published: (2025)
Approximation of the Basset force in the Maxey-Riley-Gatignol equations via universal differential equations
by: Sommer, Finn, et al.
Published: (2026)
by: Sommer, Finn, et al.
Published: (2026)
MgNO: Efficient Parameterization of Linear Operators via Multigrid
by: He, Juncai, et al.
Published: (2023)
by: He, Juncai, et al.
Published: (2023)
Learned Regularization for Inverse Problems: Insights from a Spectral Model
by: Burger, Martin, et al.
Published: (2023)
by: Burger, Martin, et al.
Published: (2023)
Regularized Random Fourier Features and Finite Element Reconstruction for Operator Learning in Sobolev Space
by: Yu, Xinyue, et al.
Published: (2025)
by: Yu, Xinyue, et al.
Published: (2025)
Generative Modelling of Stochastic Rotating Shallow Water Noise
by: Crisan, Dan, et al.
Published: (2024)
by: Crisan, Dan, et al.
Published: (2024)
Robust First and Second-Order Differentiation for Regularized Optimal Transport
by: Li, Xingjie, et al.
Published: (2024)
by: Li, Xingjie, et al.
Published: (2024)
On the existence of minimizers in shallow residual ReLU neural network optimization landscapes
by: Dereich, Steffen, et al.
Published: (2023)
by: Dereich, Steffen, et al.
Published: (2023)
On the existence of optimal shallow feedforward networks with ReLU activation
by: Dereich, Steffen, et al.
Published: (2023)
by: Dereich, Steffen, et al.
Published: (2023)
How Can Deep Neural Networks Fail Even With Global Optima?
by: Guan, Qingguang
Published: (2024)
by: Guan, Qingguang
Published: (2024)
Learning to Control the Smoothness of Graph Convolutional Network Features
by: Wang, Shih-Hsin, et al.
Published: (2024)
by: Wang, Shih-Hsin, et al.
Published: (2024)
Neural-HSS: Hierarchical Semi-Separable Neural PDE Solver
by: Sittoni, Pietro, et al.
Published: (2026)
by: Sittoni, Pietro, et al.
Published: (2026)
Randomly pivoted Cholesky: Practical approximation of a kernel matrix with few entry evaluations
by: Chen, Yifan, et al.
Published: (2022)
by: Chen, Yifan, et al.
Published: (2022)
Single-shot prediction of parametric partial differential equations
by: Rafiq, Khalid, et al.
Published: (2025)
by: Rafiq, Khalid, et al.
Published: (2025)
Embedding Inequalities for Barron-type Spaces
by: Wu, Lei
Published: (2023)
by: Wu, Lei
Published: (2023)
Approximation theory for 1-Lipschitz ResNets
by: Murari, Davide, et al.
Published: (2025)
by: Murari, Davide, et al.
Published: (2025)
Deep Symmetric Autoencoders from the Eckart-Young-Schmidt Perspective
by: Brivio, Simone, et al.
Published: (2025)
by: Brivio, Simone, et al.
Published: (2025)
Optimal Transport-inspired Deep Learning Framework for Slow-Decaying Kolmogorov n-width Problems: Exploiting Sinkhorn Loss and Wasserstein Kernel
by: Khamlich, Moaad, et al.
Published: (2023)
by: Khamlich, Moaad, et al.
Published: (2023)
Convergence for adaptive resampling of random Fourier features
by: Huang, Xin, et al.
Published: (2025)
by: Huang, Xin, et al.
Published: (2025)
Newton Informed Neural Operator for Computing Multiple Solutions of Nonlinear Partials Differential Equations
by: Hao, Wenrui, et al.
Published: (2024)
by: Hao, Wenrui, et al.
Published: (2024)
Embrace rejection: Kernel matrix approximation by accelerated randomly pivoted Cholesky
by: Epperly, Ethan N., et al.
Published: (2024)
by: Epperly, Ethan N., et al.
Published: (2024)
MgNet: A Unified Framework of Multigrid and Convolutional Neural Network
by: He, Juncai, et al.
Published: (2019)
by: He, Juncai, et al.
Published: (2019)
Physics-based deep kernel learning for parameter estimation in high dimensional PDEs
by: Yan, Weihao, et al.
Published: (2025)
by: Yan, Weihao, et al.
Published: (2025)
Finite Sample Analysis and Bounds of Generalization Error of Gradient Descent in In-Context Linear Regression
by: Duraisamy, Karthik
Published: (2024)
by: Duraisamy, Karthik
Published: (2024)
Optimization-Free Diffusion Model -- A Perturbation Theory Approach
by: Khoo, Yuehaw, et al.
Published: (2025)
by: Khoo, Yuehaw, et al.
Published: (2025)
Energy Approach from $\varepsilon$-Graph to Continuum Diffusion Model with Connectivity Functional
by: Yang, Yahong, et al.
Published: (2025)
by: Yang, Yahong, et al.
Published: (2025)
RMFlow: Refined Mean Flow by a Noise-Injection Step for Multimodal Generation
by: Huang, Yuhao, et al.
Published: (2026)
by: Huang, Yuhao, et al.
Published: (2026)
Automatic Differentiation is Essential in Training Neural Networks for Solving Differential Equations
by: Chen, Chuqi, et al.
Published: (2024)
by: Chen, Chuqi, et al.
Published: (2024)
Learn Singularly Perturbed Solutions via Homotopy Dynamics
by: Chen, Chuqi, et al.
Published: (2025)
by: Chen, Chuqi, et al.
Published: (2025)
A Second-Order TGV Discretization with $90^{\circ}$ Rotational Invariance Property
by: Hosseini, Alireza, et al.
Published: (2022)
by: Hosseini, Alireza, et al.
Published: (2022)
A space-time dual-pairing summation-by-parts framework for forward and adjoint wave equations
by: Wiratama, Kenny, et al.
Published: (2026)
by: Wiratama, Kenny, et al.
Published: (2026)
On the Dimension-Free Approximation of Deep Neural Networks for Symmetric Korobov Functions
by: Lu, Yulong, et al.
Published: (2025)
by: Lu, Yulong, et al.
Published: (2025)
A resource-efficient model for deep kernel learning
by: D'Amore, Luisa
Published: (2024)
by: D'Amore, Luisa
Published: (2024)
Similar Items
-
Deep Neural Networks with General Activations: Super-Convergence in Sobolev Norms
by: Yang, Yahong, et al.
Published: (2025) -
Deep Neural Networks and Finite Elements of Any Order on Arbitrary Dimensions
by: He, Juncai, et al.
Published: (2023) -
Towards regularized learning from functional data with covariate shift
by: Holzleitner, Markus, et al.
Published: (2026) -
Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations
by: Chen, Shuang, et al.
Published: (2026) -
Why the noise model matters: A performance gap in learned regularization
by: Banert, Sebastian, et al.
Published: (2025)