Imagen de Portada

Deep Network Trainability via Persistent Subspace Orthogonality

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Massucco, Alex, Murari, Davide, Schönlieb, Carola-Bibiane
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Numerical Analysis
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Approximation theory for 1-Lipschitz ResNets
por: Murari, Davide, et al.
Publicado: (2025)

Hamiltonian Matching for Symplectic Neural Integrators
por: Canizares, Priscilla, et al.
Publicado: (2024)

Inverse Evolution Layers: Physics-informed Regularizers for Deep Neural Networks
por: Liu, Chaoyu, et al.
Publicado: (2023)

Expressivity of Bi-Lipschitz Normalizing Flows: A Score-Based Diffusion Perspective
por: Iske, Meira, et al.
Publicado: (2026)

Data-driven approaches to inverse problems
por: Schönlieb, Carola-Bibiane, et al.
Publicado: (2025)

Christoffel-DPS: Optimal sensor placement in diffusion posterior sampling for arbitrary distributions
por: Rowbottom, James, et al.
Publicado: (2026)

SpectraKAN: Conditioning Spectral Operators
por: Cheng, Chun-Wun, et al.
Publicado: (2026)

Multi-Level Monte Carlo Training of Neural Operators
por: Rowbottom, James, et al.
Publicado: (2025)

Muon is Not That Special: Random or Inverted Spectra Work Just as Well
por: Shumaylov, Zakhar, et al.
Publicado: (2026)

PDE Solvers Should Be Local: Fast, Stable Rollouts with Learned Local Stencils
por: Cheng, Chun-Wun, et al.
Publicado: (2025)

Graph Neural Regularizers for PDE Inverse Problems
por: Lauga, William, et al.
Publicado: (2025)

HAMLET: Graph Transformer Neural Operator for Partial Differential Equations
por: Bryutkin, Andrey, et al.
Publicado: (2024)

CATO: Charted Attention for Neural PDE Operators
por: Cheng, Chun-Wun, et al.
Publicado: (2026)

Mamba Neural Operator: Who Wins? Transformers vs. State-Space Models for PDEs
por: Cheng, Chun-Wun, et al.
Publicado: (2024)

Parallel-in-Time Solutions with Random Projection Neural Networks
por: Betcke, Marta M., et al.
Publicado: (2024)

G-Adaptivity: optimised graph-based mesh relocation for finite element methods
por: Rowbottom, James, et al.
Publicado: (2024)

Approximation Theory for Lipschitz Continuous Transformers
por: Furuya, Takashi, et al.
Publicado: (2026)

Stable neural networks and connections to continuous dynamical systems
por: Ehrhardt, Matthias J., et al.
Publicado: (2025)

Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie Groups
por: Shumaylov, Zakhar, et al.
Publicado: (2024)

Predictions Based on Pixel Data: Insights from PDEs and Finite Differences
por: Celledoni, Elena, et al.
Publicado: (2023)

Deep Learning for Subspace Regression
por: Fanaskov, Vladimir, et al.
Publicado: (2025)

Multi-Headed Transformer Architectures as Time-dependent Wasserstein Gradient Flows
por: Massucco, Alex, et al.
Publicado: (2026)

When is a System Discoverable from Data? Discovery Requires Chaos
por: Shumaylov, Zakhar, et al.
Publicado: (2025)

Resilient Graph Neural Networks: A Coupled Dynamical Systems Approach
por: Eliasof, Moshe, et al.
Publicado: (2023)

Proximal Langevin Sampling With Inexact Proximal Mapping
por: Ehrhardt, Matthias J., et al.
Publicado: (2023)

Approximation properties of neural ODEs
por: De Marinis, Arturo, et al.
Publicado: (2025)

Digital Twin Data Modelling by Randomized Orthogonal Decomposition and Deep Learning
por: Bistrian, Diana Alina, et al.
Publicado: (2022)

Nested Bregman Iterations for Decomposition Problems
por: Wolf, Tobias, et al.
Publicado: (2024)

Deep Block Proximal Linearised Minimisation Algorithm for Non-convex Inverse Problems
por: Huang, Chaoyan, et al.
Publicado: (2024)

Persistent-Transient Policy Evaluation for Markov Chains via Minimal Peripheral Quotients
por: Xu, Yang, et al.
Publicado: (2026)

Spectral Clustering via Orthogonalization-Free Methods
por: Pang, Qiyuan, et al.
Publicado: (2023)

Accelerating Eigenvalue Dataset Generation via Chebyshev Subspace Filter
por: Wang, Hong, et al.
Publicado: (2025)

Orthogonal greedy algorithm for linear operator learning with shallow neural network
por: Lin, Ye, et al.
Publicado: (2025)

Low-rank adaptive physics-informed HyperDeepONets for solving differential equations
por: Zeudong, Etienne, et al.
Publicado: (2025)

Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling
por: Wang, Hong, et al.
Publicado: (2024)

Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration
por: Pourkamali-Anaraki, Farhad
Publicado: (2026)

An Orthogonal Polynomial Kernel-Based Machine Learning Model for Differential-Algebraic Equations
por: Taheri, Tayebeh, et al.
Publicado: (2024)

ChebNet: Efficient and Stable Constructions of Deep Neural Networks with Rectified Power Units via Chebyshev Approximations
por: Tang, Shanshan, et al.
Publicado: (2019)

Deep Spectral Prior
por: Cheng, Yanqi, et al.
Publicado: (2025)

Conformalized-DeepONet: A Distribution-Free Framework for Uncertainty Quantification in Deep Operator Networks
por: Moya, Christian, et al.
Publicado: (2024)