Imagen de Portada

Universality in Deep Neural Networks: An approach via the Lindeberg exchange principle

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Giovagnini, Filippo, Kotitsas, Sotirios, Romito, Marco
Formato:	Preprint
Publicado:	2026
Materias:	Probability Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

The heat equation with time-correlated random potential in d=2: Edwards-Wilkinson fluctuations
por: Kotitsas, Sotirios
Publicado: (2024)

Gaussian Fluctuations for the Stochastic Landau-Lifshitz Navier-Stokes Equation in Dimension $D\geq2$
por: Kotitsas, Sotiris, et al.
Publicado: (2025)

Effective continuous equations for adaptive SGD: a stochastic analysis view
por: Callisti, Luca, et al.
Publicado: (2025)

Stochastic Scaling Limits and Synchronization by Noise in Deep Transformer Models
por: Agazzi, Andrea, et al.
Publicado: (2026)

A uniform point vortex approximation for the solution of the two-dimensional Navier Stokes equation with transport noise
por: Giovagnini, Filippo, et al.
Publicado: (2024)

A uniform particle approximation to the Navier-Stokes-alpha models in three dimensions with advection noise
por: Giovagnini, Filippo, et al.
Publicado: (2025)

Edwards-Wilkinson limit for a stochastic advection-diffusion PDE
por: Kotitsas, Sotirios, et al.
Publicado: (2025)

Partially Stochastic Infinitely Deep Bayesian Neural Networks
por: Calvo-Ordonez, Sergio, et al.
Publicado: (2024)

Finite-Dimensional Gaussian Approximation for Deep Neural Networks: Universality in Random Weights
por: Balasubramanian, Krishnakumar, et al.
Publicado: (2025)

Stochastic Port-Hamiltonian Neural Networks: Universal Approximation with Passivity Guarantees
por: Di Persio, Luca, et al.
Publicado: (2026)

Deep Neural Networks as Iterated Function Systems and a Generalization Bound
por: Vacher, Jonathan
Publicado: (2026)

Wasserstein Convergence of Score-based Generative Models under Semiconvexity and Discontinuous Gradients
por: Bruno, Stefano, et al.
Publicado: (2025)

Total variation bounds in the Lindeberg central limit theorem
por: Dung, N. T., et al.
Publicado: (2025)

Quantitative CLTs in Deep Neural Networks
por: Favaro, Stefano, et al.
Publicado: (2023)

Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks
por: Lim, Dong-Young, et al.
Publicado: (2021)

Efficient Training of Deep Neural Operator Networks via Randomized Sampling
por: Karumuri, Sharmila, et al.
Publicado: (2024)

kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients
por: Lytras, Iosif, et al.
Publicado: (2025)

Large deviation principles for convolutional Bayesian neural networks
por: Bassetti, Federico, et al.
Publicado: (2026)

BN-Pool: Bayesian Nonparametric Pooling for Graphs
por: Castellana, Daniele, et al.
Publicado: (2025)

Approximation to Deep Q-Network by Stochastic Delay Differential Equations
por: Lu, Jianya, et al.
Publicado: (2025)

Interacting Particle Langevin Algorithm for Maximum Marginal Likelihood Estimation
por: Akyildiz, Ö. Deniz, et al.
Publicado: (2023)

Depth Degeneracy in Neural Networks: Vanishing Angles in Fully Connected ReLU Networks on Initialization
por: Jakub, Cameron, et al.
Publicado: (2023)

Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit
por: Riedl, Konstantin, et al.
Publicado: (2026)

Symmetries in Overparametrized Neural Networks: A Mean-Field View
por: Maass, Javier, et al.
Publicado: (2024)

Random ReLU Neural Networks as Non-Gaussian Processes
por: Parhi, Rahul, et al.
Publicado: (2024)

Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD
por: Wan, Yijun, et al.
Publicado: (2023)

Exact Gradients for Stochastic Spiking Neural Networks Driven by Rough Signals
por: Holberg, Christian, et al.
Publicado: (2024)

Flatness-Aware Stochastic Gradient Langevin Dynamics
por: Bruno, Stefano, et al.
Publicado: (2025)

The Performance Of The Unadjusted Langevin Algorithm Without Smoothness Assumptions
por: Johnston, Tim, et al.
Publicado: (2025)

Resolving Node Identifiability in Graph Neural Processes via Laplacian Spectral Encodings
por: Yan, Zimo, et al.
Publicado: (2025)

On diffusion-based generative models and their error bounds: The log-concave case with full convergence estimates
por: Bruno, Stefano, et al.
Publicado: (2023)

Pointwise Generalization in Deep Neural Networks
por: Li, Shaojie, et al.
Publicado: (2026)

Neural Continuous-Time Markov Chain: Discrete Diffusion via Decoupled Jump Timing and Direction
por: Li, Jingyuan, et al.
Publicado: (2026)

Bayesian Inference with Deep Weakly Nonlinear Networks
por: Hanin, Boris, et al.
Publicado: (2024)

Existence of Adversarial Examples for Random Convolutional Networks via Isoperimetric Inequalities on $\mathbb{so}(d)$
por: Daniely, Amit
Publicado: (2025)

Langevin dynamics based algorithm e-TH$\varepsilon$O POULA for stochastic optimization problems with discontinuous stochastic gradient
por: Lim, Dong-Young, et al.
Publicado: (2022)

Network reconstruction via the minimum description length principle
por: Peixoto, Tiago P.
Publicado: (2024)

Neural Network Parameter-optimization of Gaussian pmDAGs
por: Saremi, Mehrzad
Publicado: (2023)

Feature Learning Dynamics in Infinite-Depth Neural Networks
por: Yao, Zihan, et al.
Publicado: (2025)

Unified Stochastic Framework for Neural Network Quantization and Pruning
por: Zhang, Haoyu, et al.
Publicado: (2024)