Cover Image

Multiple Descents in Deep Learning as a Sequence of Order-Chaos Transitions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wei, Wenbo, Le, Nicholas Chong Jia, Lai, Choy Heng, Feng, Ling
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Chaotic Dynamics Computational Physics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective
by: Hu, Jiaxi, et al.
Published: (2024)

ChaosNetBench: Benchmarking Spatio-Temporal Graph Neural Networks on Chaotic Lattice Dynamics
by: Moges, Henok Tenaw, et al.
Published: (2026)

From Complex Dynamics to DynFormer: Rethinking Transformers for PDEs
by: Lai, Pengyu, et al.
Published: (2026)

When is a System Discoverable from Data? Discovery Requires Chaos
by: Shumaylov, Zakhar, et al.
Published: (2025)

Gradient Flossing: Improving Gradient Descent through Dynamic Control of Jacobians
by: Engelken, Rainer
Published: (2023)

LanTu: Dynamics-Enhanced Deep Learning for Eddy-Resolving Ocean Forecasting
by: Zheng, Qingyu, et al.
Published: (2025)

Horizon-Constrained Rashomon Sets for Chaotic Forecasting
by: Kale, Gauri, et al.
Published: (2026)

True Zero-Shot Inference of Dynamical Systems Preserving Long-Term Statistics
by: Hemmer, Christoph Jürgen, et al.
Published: (2025)

Out-of-Domain Generalization in Dynamical Systems Reconstruction
by: Göring, Niclas, et al.
Published: (2024)

Optimal Recurrent Network Topologies for Dynamical Systems Reconstruction
by: Hemmer, Christoph Jürgen, et al.
Published: (2024)

Unsupervised learning for anticipating critical transitions
by: Panahi, Shirin, et al.
Published: (2025)

Universal Second-Order Phase Transition from Integrability to Chaos
by: Leonel, Edson D., et al.
Published: (2026)

Uncovering the Computational Roles of Nonlinearity in Sequence Modeling Using Almost-Linear RNNs
by: Brenner, Manuel, et al.
Published: (2025)

Network Dynamics-Based Framework for Understanding Deep Neural Networks
by: Lin, Yuchen, et al.
Published: (2025)

Data assimilation and discrepancy modeling with shallow recurrent decoders
by: Bao, Yuxuan, et al.
Published: (2025)

DyMixOp: A Neural Operator Designed from a Complex Dynamics Perspective with Local-Global Mixing for Solving PDEs
by: Lai, Pengyu, et al.
Published: (2025)

Artificial Intelligence for EEG Prediction: Applied Chaos Theory
by: Jorgsson, Vincent
Published: (2023)

Deep Learning for Prediction and Classifying the Dynamical behaviour of Piecewise Smooth Maps
by: S, Vismaya V, et al.
Published: (2024)

Dynamics-Informed Deep Learning for Predicting Extreme Events
by: Katsidoniotaki, Eirini, et al.
Published: (2026)

Learning with Mandelbrot and Julia
by: Tjahjono, V. R., et al.
Published: (2025)

Transformers for dynamical systems learn transfer operators in-context
by: Bao, Anthony, et al.
Published: (2026)

Using Machine Learning and Neural Networks to Analyze and Predict Chaos in Multi-Pendulum and Chaotic Systems
by: Ramachandruni, Vasista, et al.
Published: (2025)

Reduced-Order Modeling of Cyclo-Stationary Time Series Using Score-Based Generative Methods
by: Giorgini, Ludovico Theo, et al.
Published: (2025)

Deep Learning of the Evolution Operator Enables Forecasting of Out-of-Training Dynamics in Chaotic Systems
by: Shokar, Ira J. S., et al.
Published: (2025)

Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data
by: Brenner, Manuel, et al.
Published: (2024)

Unsupervised Learning in Echo State Networks for Input Reconstruction
by: Yamada, Taiki, et al.
Published: (2025)

Generative Lagrangian data assimilation for ocean dynamics under extreme sparsity
by: Asefi, Niloofar, et al.
Published: (2025)

OceanNet: A principled neural operator-based digital twin for regional oceans
by: Chattopadhyay, Ashesh, et al.
Published: (2023)

Tree-based Learning for High-Fidelity Prediction of Chaos
by: Giammarese, Adam, et al.
Published: (2024)

Deficiency of equation-finding approach to data-driven modeling of dynamical systems
by: Zhai, Zheng-Meng, et al.
Published: (2025)

Order and Chaos in Systems of Coaxial Vortex Pairs
by: Mavroyiakoumou, Christiana, et al.
Published: (2025)

The Supersymmetric Origin of Chaos and its Hidden Topological Order
by: Ovchinnikov, Igor V., et al.
Published: (2026)

A Novel Approach for Estimating Largest Lyapunov Exponents in One-Dimensional Chaotic Time Series Using Machine Learning
by: Velichko, A., et al.
Published: (2025)

Predicting Chaotic System Behavior using Machine Learning Techniques
by: Rao, Huaiyuan, et al.
Published: (2024)

Machine Learning for Predicting Chaotic Systems
by: Schötz, Christof, et al.
Published: (2024)

Reservoir observer enhanced with residual calibration and attention mechanism
by: Liu, Yichen, et al.
Published: (2026)

Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction
by: Brenner, Manuel, et al.
Published: (2024)

Structured Kolmogorov-Arnold Neural ODEs for Interpretable Learning and Symbolic Discovery of Nonlinear Dynamics
by: Liu, Wei, et al.
Published: (2025)

Incorporating Coupling Knowledge into Echo State Networks for Learning Spatiotemporally Chaotic Dynamics
by: Chu, Kuei-Jan, et al.
Published: (2025)

Trans-Bifurcation Prediction of Dynamics in terms of Extreme Learning Machines with Control Inputs
by: Tadokoro, Satoru, et al.
Published: (2024)