Cover Image

The Hidden Width of Deep ResNets: Tight Error Bounds and Phase Diagram

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Chizat, Lénaïc
Format:	Preprint
Published:	2025
Subjects:	Machine Learning 68T07, 60H30, 34F05
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Phase Diagram of Dropout for Two-Layer Neural Networks in the Mean-Field Regime
by: Chizat, Lénaïc, et al.
Published: (2025)

Large deviations of one-hidden-layer neural networks
by: Hirsch, Christian, et al.
Published: (2024)

Universal Approximation Constraints of Narrow ResNets: The Tunnel Effect
by: Kuehn, Christian, et al.
Published: (2026)

The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks
by: Chizat, Lénaïc, et al.
Published: (2023)

$\mathbb{L}^p$-solution of generalized BSDEs in a general filtration with stochastic monotone coefficients
by: Elmansouri, Badr, et al.
Published: (2025)

Constructive Universal Approximation and Finite Sample Memorization by Narrow Deep ReLU Networks
by: Hernández, Martín, et al.
Published: (2024)

Doubly Reflected BSDEs with default time under stochastic Lipschitz coefficients and Applications
by: Elmansouri, Badr, et al.
Published: (2025)

Posterior Bayesian Neural Networks with Dependent Weights
by: Apollonio, Nicola, et al.
Published: (2025)

Deep Operator BSDE: a Numerical Scheme to Approximate Solution Operators
by: Lozano, Pere Díaz, et al.
Published: (2024)

Uniform-in-time convergence bounds for Persistent Contrastive Divergence Algorithms
by: Oliva, Paul Felix Valsecchi, et al.
Published: (2025)

Score-based constrained generative modeling via Langevin diffusions with boundary conditions
by: Nordenhög, Adam, et al.
Published: (2025)

Terminally constrained flow-based generative models from an optimal control perspective
by: Gao, Weiguo, et al.
Published: (2026)

Modified wavelet variation for the Hermite processes
by: Loosveldt, Laurent, et al.
Published: (2024)

Neural Networks as Local-to-Global Computations
by: Bosca, Vicente, et al.
Published: (2026)

Rivers under Noise
by: Scheutzow, Michael, et al.
Published: (2024)

Symbolic Branch Networks: Tree-Inherited Neural Models for Interpretable Multiclass Classification
by: Rodríguez-Salas, Dalia
Published: (2025)

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

Error analysis for learning fractional stochastic differential equations with applications in neural approximations
by: Dehshiri, Mahdi, et al.
Published: (2026)

Large and moderate deviations for Gaussian neural networks
by: Macci, Claudio, et al.
Published: (2024)

Functional SDE approximation inspired by a deep operator network architecture
by: Eigel, Martin, et al.
Published: (2024)

Adaptive deep density approximation for stochastic dynamical systems
by: He, Junjie, et al.
Published: (2024)

On a Stochastic Differential Equation with Correction Term Governed by a Monotone and Lipschitz Continuous Operator
by: Bot, Radu Ioan, et al.
Published: (2024)

Permutation recovery of spikes in noisy high-dimensional tensor estimation
by: Arous, Gérard Ben, et al.
Published: (2024)

A Malliavin-Gamma calculus approach to Score Based Diffusion Generative models for random fields
by: Greco, Giacomo
Published: (2025)

Constructive interpolation and generalization rates for neural ODEs: a control perspective
by: Álvarez-López, Antonio, et al.
Published: (2026)

Continuous-time Online Learning via Mean-Field Neural Networks: Regret Analysis in Diffusion Environments
by: Bayraktar, Erhan, et al.
Published: (2026)

Density convergence on Markov diffusion chaos via Stein's method
by: Dang, Thanh, et al.
Published: (2025)

Non-central limit of densities of some functionals of Gaussian processes
by: Bourguin, Solesne, et al.
Published: (2024)

Quantitative Fluctuation Analysis for Continuous-Time Stochastic Gradient Descent via Malliavin Calculus
by: Bourguin, Solesne, et al.
Published: (2026)

Superpositions for General Conditional Mckean-Vlasov Stochastic Differential Equations
by: Feng, Qi, et al.
Published: (2025)

A new architecture of high-order deep neural networks that learn martingales
by: Ninomiya, Syoiti, et al.
Published: (2025)

Cluster-based classification with neural ODEs via control
by: Álvarez-López, Antonio, et al.
Published: (2023)

Efficient Binary Decision Diagram Manipulation in External Memory
by: Sølvsten, Steffan Christ, et al.
Published: (2021)

Geometric Asymptotics of Score Mixing and Guidance in Diffusion Models
by: Liu, Kang, et al.
Published: (2026)

Measuring and Decomposing Mode Separation via the Canonical Diffusion
by: Tolkovsky, Shaul, et al.
Published: (2026)

A forward differential deep learning-based algorithm for solving high-dimensional nonlinear backward stochastic differential equations
by: Kapllani, Lorenc, et al.
Published: (2024)

A backward differential deep learning-based algorithm for solving high-dimensional nonlinear backward stochastic differential equations
by: Kapllani, Lorenc, et al.
Published: (2024)

Local Lipschitz continuity in the initial value and strong completeness for nonlinear stochastic differential equations
by: Cox, Sonja, et al.
Published: (2013)

Large Deviations of Gaussian Neural Networks with ReLU activation
by: Vogel, Quirin
Published: (2024)

Manifold Percolation: from generative model to Reinforce learning
by: Tong, Rui
Published: (2025)