Image de couverture de livre

How Can Deep Neural Networks Fail Even With Global Optima?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Guan, Qingguang
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Numerical Analysis 68T07, 65Z05, 65D99
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Neural-HSS: Hierarchical Semi-Separable Neural PDE Solver
par: Sittoni, Pietro, et autres
Publié: (2026)

Vanilla Feedforward Neural Networks as a Discretization of Dynamical Systems
par: Duan, Yifei, et autres
Publié: (2022)

Minimum Width of Leaky-ReLU Neural Networks for Uniform Universal Approximation
par: Li, Li'ang, et autres
Publié: (2023)

Physics-Informed Neural Networks: A Didactic Derivation of the Complete Training Cycle
par: Tahimi, Abdeladhim
Publié: (2026)

Coupling-Robust Accuracy in Multiphysics Physics Informed Neural Networks via Kronecker-Preconditioned Optimization
par: Park, Youngjae, et autres
Publié: (2026)

A Structure-Preserving Framework for Solving Parabolic Partial Differential Equations with Neural Networks
par: Chen, Gaohang, et autres
Publié: (2025)

A Modular Deep Learning-based Approach for Diffuse Optical Tomography Reconstruction
par: Benfenati, Alessandro, et autres
Publié: (2024)

Deep Neural Networks and Finite Elements of Any Order on Arbitrary Dimensions
par: He, Juncai, et autres
Publié: (2023)

Separable Physics-Informed Neural Networks for the solution of elasticity problems
par: Es'kin, Vasiliy A., et autres
Publié: (2024)

Deep Neural ODE Operator Networks for PDEs
par: Li, Ziqian, et autres
Publié: (2025)

Enforcing boundary conditions for physics-informed neural operators
par: Göschel, Niklas, et autres
Publié: (2025)

Capturing Shock Waves by Relaxation Neural Networks
par: Zhou, Nan, et autres
Publié: (2024)

RONOM: Reduced-Order Neural Operator Modeling
par: Dummer, Sven, et autres
Publié: (2025)

Data Completion for Electrical Impedance Tomography by Conditional Diffusion Models
par: Chen, Ke, et autres
Publié: (2026)

A Minimal Control Family of Dynamical Systems for Universal Approximation
par: Duan, Yifei, et autres
Publié: (2023)

Deep Micro Solvers for Rough-Wall Stokes Flow in a Heterogeneous Multiscale Method
par: Ström, Emanuel, et autres
Publié: (2025)

Neural Ordinary Differential Equations for Model Order Reduction of Stiff Systems
par: Caldana, Matteo, et autres
Publié: (2024)

Deep asymptotic expansion method for solving singularly perturbed time-dependent reaction-advection-diffusion equations
par: Zhu, Qiao, et autres
Publié: (2025)

Accuracy and stability of Artificial Neural Networks for HP-Splines frequency parameter selection
par: Bruni, Vittoria, et autres
Publié: (2026)

Are Two Hidden Layers Still Enough for the Physics-Informed Neural Networks?
par: Es'kin, Vasiliy A., et autres
Publié: (2024)

About rectified sigmoid function for enhancing the accuracy of Physics-Informed Neural Networks
par: Es'kin, Vasiliy A., et autres
Publié: (2024)

Neural Network Element Method for Partial Differential Equations
par: Wang, Yifan, et autres
Publié: (2025)

Equidistribution-based training of Free Knot Splines and ReLU Neural Networks
par: Appella, Simone, et autres
Publié: (2024)

Learn and Verify: A Framework for Rigorous Verification of Physics-Informed Neural Networks
par: Tanaka, Kazuaki, et autres
Publié: (2026)

High order positivity-preserving numerical methods for a non-local photochemical model
par: Pezzella, Mario
Publié: (2025)

Regularity Analysis and Tensor Neural Network Methods for Quasiperiodic Elliptic Equations
par: Ren, Jingze, et autres
Publié: (2026)

Deep Operator BSDE: a Numerical Scheme to Approximate Solution Operators
par: Lozano, Pere Díaz, et autres
Publié: (2024)

Stochastic approach for elliptic problems in perforated domains
par: Han, Jihun, et autres
Publié: (2024)

Solving High Dimensional Partial Differential Equations Using Tensor Neural Network and A Posteriori Error Estimators
par: Wang, Yifan, et autres
Publié: (2023)

Randomly pivoted Cholesky: Practical approximation of a kernel matrix with few entry evaluations
par: Chen, Yifan, et autres
Publié: (2022)

Deep Learning without Global Optimization by Random Fourier Neural Networks
par: Davis, Owen, et autres
Publié: (2024)

Achieving Universal Approximation and Universal Interpolation via Nonlinearity of Control Families
par: Cai, Yongqiang, et autres
Publié: (2025)

Learning Geometric-Aware Quadrature Rules for Functional Minimization
par: Smaragdakis, Costas
Publié: (2025)

Learning on the Temporal Tangent Bundle for Physics-Informed Neural Networks
par: Jamal, Adetola, et autres
Publié: (2026)

A coupled Kolmogorov-Arnold Network and Level-Set framework for evolving interfaces
par: Pande, Tarus, et autres
Publié: (2026)

Convergence for adaptive resampling of random Fourier features
par: Huang, Xin, et autres
Publié: (2025)

Embrace rejection: Kernel matrix approximation by accelerated randomly pivoted Cholesky
par: Epperly, Ethan N., et autres
Publié: (2024)

Symplectic integrators for second-order linear non-autonomous equations
par: Bader, Philipp, et autres
Publié: (2017)

Error bounds for Physics Informed Neural Networks in Nonlinear Schrödinger equations placed on unbounded domains
par: Alejo, Miguel Á., et autres
Publié: (2024)

Regularity and tailored regularization of Deep Neural Networks, with application to parametric PDEs in uncertainty quantification
par: Keller, Alexander, et autres
Publié: (2025)