Cover Image

ResNets of All Shapes and Sizes: Convergence of Training Dynamics in the Large-scale Limit

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chaintron, Louis-Pierre, Chizat, Lénaïc, Maass, Javier
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Probability
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Hidden Width of Deep ResNets: Tight Error Bounds and Phase Diagram
by: Chizat, Lénaïc
Published: (2025)

Deep linear networks for regression are implicitly regularized towards flat minima
by: Marion, Pierre, et al.
Published: (2024)

Annealed Sinkhorn for Optimal Transport: convergence, regularization path and debiasing
by: Chizat, Lénaïc
Published: (2024)

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

Approximating Langevin Monte Carlo with ResNet-like Neural Network architectures
by: Miranda, Charles, et al.
Published: (2023)

An Exponentially Converging Particle Method for the Mixed Nash Equilibrium of Continuous Games
by: Wang, Guillaume, et al.
Published: (2022)

Doubly Regularized Entropic Wasserstein Barycenters
by: Chizat, Lénaïc
Published: (2023)

Scaling ResNets in the Large-depth Regime
by: Marion, Pierre, et al.
Published: (2022)

Quasi-continuity method for mean-field diffusions: large deviations and central limit theorem
by: Chaintron, Louis-Pierre
Published: (2024)

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

Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach
by: Wang, Guillaume, et al.
Published: (2024)

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

Regularity and stability for the Gibbs conditioning principle on path space via McKean-Vlasov control
by: Chaintron, Louis-Pierre, et al.
Published: (2024)

On Dissipativity of Cross-Entropy Loss in Training ResNets
by: Püttschneider, Jens, et al.
Published: (2024)

Towards an Optimal Control Perspective of ResNet Training
by: Püttschneider, Jens, et al.
Published: (2025)

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

Geodesic convexity and strengthened functional inequalities in submanifolds of Wasserstein space
by: Chaintron, Louis-Pierre, et al.
Published: (2025)

Optimal rate of convergence in the vanishing viscosity for quadratic Hamilton-Jacobi equations
by: Chaintron, Louis-Pierre, et al.
Published: (2025)

Progressive Feedforward Collapse of ResNet Training
by: Wang, Sicong, et al.
Published: (2024)

Quantitative Convergence of Wasserstein Gradient Flows of Kernel Mean Discrepancies
by: Chizat, Lénaïc, et al.
Published: (2026)

ResNets Are Deeper Than You Think
by: Mehmeti-Göpel, Christian H. X. Ali, et al.
Published: (2025)

L-Lipschitz Gershgorin ResNet Network
by: Juston, Marius F. R., et al.
Published: (2025)

Transformative or Conservative? Conservation laws for ResNets and Transformers
by: Marcotte, Sibylle, et al.
Published: (2025)

Deep Learning as a Convex Paradigm of Computation: Minimizing Circuit Size with ResNets
by: Jacot, Arthur
Published: (2025)

Uniform Scaling Limits in AdamW-Trained Transformers
by: Gibson, William, et al.
Published: (2026)

Quantitative Local Convergence of Mean-Field Stein Variational Gradient Flow
by: Chizat, Lénaïc, et al.
Published: (2026)

Efficient Gravitational Wave Parameter Estimation via Knowledge Distillation: A ResNet1D-IAF Approach
by: Zhu, Xihua, et al.
Published: (2024)

Convergence, Sticking and Escape: Stochastic Dynamics Near Critical Points in SGD
by: Dudukalov, Dmitry, et al.
Published: (2025)

Interpreting the Residual Stream of ResNet18
by: Longon, André
Published: (2024)

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

Generalization of Scaled Deep ResNets in the Mean-Field Regime
by: Chen, Yihang, et al.
Published: (2024)

Bridging Neural ODE and ResNet: A Formal Error Bound for Safety Verification
by: Sayed, Abdelrahman Sayed, et al.
Published: (2025)

Convergent Stochastic Training of Attention and Understanding LoRA
by: Sun, Zhengkai, et al.
Published: (2026)

Convergence of SGD for Training Neural Networks with Sliced Wasserstein Losses
by: Tanguy, Eloi
Published: (2023)

Gibbs principle with infinitely many constraints: optimality conditions and stability
by: Chaintron, Louis-Pierre, et al.
Published: (2024)

Propagation of weak log-concavity along generalised heat flows via Hamilton-Jacobi equations
by: Chaintron, Louis-Pierre, et al.
Published: (2025)

Collective Kernel EFT for Pre-activation ResNets
by: Kawase, Hidetoshi, et al.
Published: (2026)

Field theory for optimal signal propagation in ResNets
by: Fischer, Kirsten, et al.
Published: (2023)

On the inductive bias of infinite-depth ResNets and the bottleneck rank
by: Boix-Adsera, Enric
Published: (2025)

Langevin Monte-Carlo Provably Learns Depth Two Neural Nets at Any Size and Data
by: Kumar, Dibyakanti, et al.
Published: (2025)