On the Generalization Behavior of Deep Residual Networks From a Dynamical System Perspective
Fuente:
arXiv
Saved in:
| Main Authors: | Huang, Jinshu, Sun, Mingfei, Wu, Chunlin |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Mathematical Modeling and Convergence Analysis of Deep Neural Networks with Dense Layer Connectivities in Deep Learning
by: Huang, Jinshu, et al.
Published: (2025)
by: Huang, Jinshu, et al.
Published: (2025)
Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation
by: Sun, Mingfei
Published: (2026)
by: Sun, Mingfei
Published: (2026)
Regularized Gradient Clipping Provably Trains Wide and Deep Neural Networks
by: Tucat, Matteo, et al.
Published: (2024)
by: Tucat, Matteo, et al.
Published: (2024)
Deep-layer limit and stability analysis of the basic forward-backward-splitting induced network (II): learning problems
by: Lin, Xuan, et al.
Published: (2026)
by: Lin, Xuan, et al.
Published: (2026)
Deep Convolutional Neural Networks for Palm Fruit Maturity Classification
by: Han, Mingqiang, et al.
Published: (2025)
by: Han, Mingqiang, et al.
Published: (2025)
Task-Driven Kernel Flows: Label Rank Compression and Laplacian Spectral Filtering
by: Li, Hongxi, et al.
Published: (2026)
by: Li, Hongxi, et al.
Published: (2026)
A Qualitative Test-Risk Mechanism for Scaling Behavior in Normalized Residual Networks
by: Cheng, Daning, et al.
Published: (2026)
by: Cheng, Daning, et al.
Published: (2026)
Generalized Cauchy-Schwarz Divergence and Its Deep Learning Applications
by: Lu, Mingfei, et al.
Published: (2024)
by: Lu, Mingfei, et al.
Published: (2024)
From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics
by: Liu, Qinshuo, et al.
Published: (2025)
by: Liu, Qinshuo, et al.
Published: (2025)
Optimal Condition for Initialization Variance in Deep Neural Networks: An SGD Dynamics Perspective
by: Horii, Hiroshi, et al.
Published: (2025)
by: Horii, Hiroshi, et al.
Published: (2025)
Residual Kolmogorov-Arnold Network for Enhanced Deep Learning
by: Yu, Ray Congrui, et al.
Published: (2024)
by: Yu, Ray Congrui, et al.
Published: (2024)
Residual Hyperbolic Graph Convolution Networks
by: Xue, Yangkai, et al.
Published: (2024)
by: Xue, Yangkai, et al.
Published: (2024)
Progressive Approximation in Deep Residual Networks: Theory and Validation
by: Wang, Wei, et al.
Published: (2026)
by: Wang, Wei, et al.
Published: (2026)
TextResNet: Decoupling and Routing Optimization Signals in Compound AI Systems via Deep Residual Tuning
by: Huang, Suizhi, et al.
Published: (2026)
by: Huang, Suizhi, et al.
Published: (2026)
Multi-Head Residual-Gated DeepONet for Coherent Nonlinear Wave Dynamics
by: Fan, Zhiwei, et al.
Published: (2026)
by: Fan, Zhiwei, et al.
Published: (2026)
Residual Alignment: Uncovering the Mechanisms of Residual Networks
by: Li, Jianing, et al.
Published: (2024)
by: Li, Jianing, et al.
Published: (2024)
Generalized Evidential Deep Learning: From a Bayesian Perspective
by: Liu, Yuanye, et al.
Published: (2026)
by: Liu, Yuanye, et al.
Published: (2026)
From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks
by: Dominé, Clémentine C. J., et al.
Published: (2024)
by: Dominé, Clémentine C. J., et al.
Published: (2024)
Rank-1 Approximation of Inverse Fisher for Natural Policy Gradients in Deep Reinforcement Learning
by: Huo, Yingxiao, et al.
Published: (2026)
by: Huo, Yingxiao, et al.
Published: (2026)
Residual Deep Gaussian Processes on Manifolds
by: Wyrwal, Kacper, et al.
Published: (2024)
by: Wyrwal, Kacper, et al.
Published: (2024)
PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation
by: Zhang, Junru, et al.
Published: (2026)
by: Zhang, Junru, et al.
Published: (2026)
Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective
by: Wang, Senmiao, et al.
Published: (2025)
by: Wang, Senmiao, et al.
Published: (2025)
Bayesian Natural Gradient Fine-Tuning of CLIP Models via Kalman Filtering
by: Abdi, Hossein, et al.
Published: (2025)
by: Abdi, Hossein, et al.
Published: (2025)
How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective
by: Zhang, Qiaozhe, et al.
Published: (2023)
by: Zhang, Qiaozhe, et al.
Published: (2023)
A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective
by: Shi, Lianghe, et al.
Published: (2025)
by: Shi, Lianghe, et al.
Published: (2025)
PirateNets: Physics-informed Deep Learning with Residual Adaptive Networks
by: Wang, Sifan, et al.
Published: (2024)
by: Wang, Sifan, et al.
Published: (2024)
A Lightweight Deep Learning Model for Automatic Modulation Classification using Dual Path Deep Residual Shrinkage Network
by: Suman, Prakash, et al.
Published: (2025)
by: Suman, Prakash, et al.
Published: (2025)
Lorentzian Residual Neural Networks
by: He, Neil, et al.
Published: (2024)
by: He, Neil, et al.
Published: (2024)
Optimization of Deep Learning Models for Dynamic Market Behavior Prediction
by: Zhao, Shenghan, et al.
Published: (2025)
by: Zhao, Shenghan, et al.
Published: (2025)
Deep Neural Networks as Iterated Function Systems and a Generalization Bound
by: Vacher, Jonathan
Published: (2026)
by: Vacher, Jonathan
Published: (2026)
Improving Generalization of Deep Neural Networks by Optimum Shifting
by: Zhou, Yuyan, et al.
Published: (2024)
by: Zhou, Yuyan, et al.
Published: (2024)
Learning the Topology and Behavior of Discrete Dynamical Systems
by: Qiu, Zirou, et al.
Published: (2024)
by: Qiu, Zirou, et al.
Published: (2024)
A priori Estimates for Deep Residual Network in Continuous-time Reinforcement Learning
by: Yin, Shuyu, et al.
Published: (2024)
by: Yin, Shuyu, et al.
Published: (2024)
Stability and Generalization for Bellman Residuals
by: Kang, Enoch H., et al.
Published: (2025)
by: Kang, Enoch H., et al.
Published: (2025)
Deep Neural Networks via Complex Network Theory: a Perspective
by: La Malfa, Emanuele, et al.
Published: (2024)
by: La Malfa, Emanuele, et al.
Published: (2024)
Dynamics of the Transformer Residual Stream: Coupling Spectral Geometry to Network Topology
by: Fernando, Jesseba, et al.
Published: (2026)
by: Fernando, Jesseba, et al.
Published: (2026)
When No-Rejection Learning is Consistent for Regression with Rejection
by: Li, Xiaocheng, et al.
Published: (2023)
by: Li, Xiaocheng, et al.
Published: (2023)
Learning to Make Adherence-Aware Advice
by: Chen, Guanting, et al.
Published: (2023)
by: Chen, Guanting, et al.
Published: (2023)
DeepCrossAttention: Supercharging Transformer Residual Connections
by: Heddes, Mike, et al.
Published: (2025)
by: Heddes, Mike, et al.
Published: (2025)
Dissipative Latent Residual Physics-Informed Neural Networks for Modeling and Identification of Electromechanical Systems
by: Long, Youyuan, et al.
Published: (2026)
by: Long, Youyuan, et al.
Published: (2026)
Similar Items
-
Mathematical Modeling and Convergence Analysis of Deep Neural Networks with Dense Layer Connectivities in Deep Learning
by: Huang, Jinshu, et al.
Published: (2025) -
Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation
by: Sun, Mingfei
Published: (2026) -
Regularized Gradient Clipping Provably Trains Wide and Deep Neural Networks
by: Tucat, Matteo, et al.
Published: (2024) -
Deep-layer limit and stability analysis of the basic forward-backward-splitting induced network (II): learning problems
by: Lin, Xuan, et al.
Published: (2026) -
Deep Convolutional Neural Networks for Palm Fruit Maturity Classification
by: Han, Mingqiang, et al.
Published: (2025)