paper-with-me

홈 › Papers

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

2025-09-12 · Lénaïc Chizat arxiv

We study the gradient-based training of large-depth residual networks (ResNets) from standard random initializations. We show that infinite-depth ResNets behave as if they were infinitely wide, regardless of their actual width. More precisely, we obtain that with a fixed embedding dimension $D$, the training dynamics converges to a unique Neural Mean ODE training dynamics as the depth $L$ diverges, regardless of the scaling of the hidden width $M$. For a residual scale $Θ_D\big(\fracα{LM}\big)$ with $α=Θ_D(1)$, we obtain the error bound $O_D\big(\frac{1}{L}+ \frac{1}{\sqrt{LM}}\big)$ between the model's output and its limit after a fixed number gradient of steps. In this regime, the limit exhibits maximal local feature updates, i.e. the Mean ODE is genuinely non-linearly parameterized. In contrast, we show that $α\to \infty$ yields a lazy ODE regime where the Mean ODE is linearly parameterized, and we derive a convergence rate in this case as well. We then focus on the particular case of ResNets with two-layer perceptron blocks, for which we study how these scalings depend on the embedding dimension $D$. We identify the residual scale $O\big(\frac{\sqrt{D}}{LM}\big)$ as necessary and sufficient for maximal local feature updates. In this regime, we prove a high-probability error bound $O\big(\frac{1}{L}+ \frac{\sqrt{D}}{\sqrt{LM}}\big)$ between the ResNet and its limit after a fixed number of gradient steps. Our convergence results rely on a novel mathematical perspective on ResNets : (i) due to the randomness of the initialization, the forward and backward pass through the ResNet behave as the stochastic approximation of certain mean ODEs, and (ii) by propagation of chaos (that is, asymptotic independence of the units) this behavior is preserved through the training dynamics. We verify empirically that all our rates are tight.

📄 PDF Abstract BibTeX arXiv:2509.10167

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On Tighter Generalization Bounds for Deep Neural Networks: CNNs, ResNets, and Beyond

2019-05-01 · ICLR 2019 5 · Xingguo Li, Junwei Lu, Zhaoran Wang, Jarvis Haupt 외

We propose a generalization error bound for a general family of deep neural networks based on the depth and width of the networks, as well as the spectral norm of weight matrices. Through introducing a novel characteriza…

Generalization Bounds

On Tighter Generalization Bound for Deep Neural Networks: CNNs, ResNets, and Beyond

2018-06-13 · Xingguo Li, Junwei Lu, Zhaoran Wang, Jarvis Haupt 외

We establish a margin based data dependent generalization error bound for a general family of deep neural networks in terms of the depth and width, as well as the Jacobian of the networks. Through introducing a new chara…

Generalization Bounds

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

2026-03-18 · Louis-Pierre Chaintron, Lénaïc Chizat, Javier Maass arxiv

We establish convergence of the training dynamics of residual neural networks (ResNets) to their joint infinite depth L, hidden width M, and embedding dimension D limit. Specifically, we consider ResNets with two-layer p…

Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks

2020-12-21 · Quynh Nguyen, Marco Mondelli, Guido Montufar

A recent line of work has analyzed the theoretical properties of deep neural networks via the Neural Tangent Kernel (NTK). In particular, the smallest eigenvalue of the NTK has been related to the memorization capacity, …

Memorization

Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods

2024-10-13 · Hossein Taheri, Christos Thrampoulidis, Arya Mazumdar

In this paper, we study the data-dependent convergence and generalization behavior of gradient methods for neural networks with smooth activation. Our first result is a novel bound on the excess risk of deep networks tra…