Cover Image

Training instability in deep learning follows low-dimensional dynamical principles

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Zhipeng, Yao, Zhenjie, Li, Kai, Yang, Lei
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Stable but Wrong: When More Data Degrades Scientific Conclusions
by: Zhang, Zhipeng, et al.
Published: (2026)

Memorization in deep learning: A survey
by: Wei, Jiaheng, et al.
Published: (2024)

Learning to Trust Experience: A Monitor-Trust-Regulator Framework for Learning under Unobservable Feedback Reliability
by: Zhang, Zhipeng, et al.
Published: (2026)

Meta-Cognitive Reinforcement Learning with Self-Doubt and Recovery
by: Zhang, Zhipeng, et al.
Published: (2026)

LLMs learn governing principles of dynamical systems, revealing an in-context neural scaling law
by: Liu, Toni J. B., et al.
Published: (2024)

Optimization of geological carbon storage operations with multimodal latent dynamic model and deep reinforcement learning
by: Wang, Zhongzheng, et al.
Published: (2024)

Economic span selection of bridge based on deep reinforcement learning
by: Zhang, Leye, et al.
Published: (2024)

Improved deep learning of chaotic dynamical systems with multistep penalty losses
by: Chakraborty, Dibyajyoti, et al.
Published: (2024)

Zero-Sacrifice Persistent-Robustness Adversarial Defense for Pre-Trained Encoders
by: Lei, Zhuxin, et al.
Published: (2026)

An approach of deep reinforcement learning for maximizing the net present value of stochastic projects
by: Xu, Wei, et al.
Published: (2025)

Learning Can Converge Stably to the Wrong Belief under Latent Reliability
by: Zhang, Zhipeng, et al.
Published: (2026)

Three-dimensional attention Transformer for state evaluation in real-time strategy games
by: Ye, Yanqing, et al.
Published: (2025)

Ultra-short-term solar power forecasting by deep learning and data reconstruction
by: Wang, Jinbao, et al.
Published: (2025)

FlexMS is a flexible framework for benchmarking deep learning-based mass spectrum prediction tools in metabolomics
by: Zhong, Yunhua, et al.
Published: (2026)

Preventing overfitting in deep learning using differential privacy
by: Khatri, Alizishaan Anwar Hussein
Published: (2026)

Continual Learning for Smart City: A Survey
by: Yang, Li, et al.
Published: (2024)

A Survey of Route Recommendations: Methods, Applications, and Opportunities
by: Zhang, Shiming, et al.
Published: (2024)

A comparative study of deep learning and ensemble learning to extend the horizon of traffic forecasting
by: Zheng, Xiao, et al.
Published: (2025)

Not all tokens are needed(NAT): token efficient reinforcement learning
by: Sang, Hejian, et al.
Published: (2026)

Spatiotemporal deep learning models for detection of rapid intensification in cyclones
by: Sutar, Vamshika, et al.
Published: (2025)

A deep learning and machine learning approach to predict neonatal death in the context of São Paulo
by: Raihan, Mohon, et al.
Published: (2025)

Latent-Space Contrastive Reinforcement Learning for Stable and Efficient LLM Reasoning
by: Shan, Lianlei, et al.
Published: (2026)

HEART: Achieving Timely Multi-Model Training for Vehicle-Edge-Cloud-Integrated Hierarchical Federated Learning
by: Yang, Xiaohong, et al.
Published: (2025)

Efficiency optimization of large-scale language models based on deep learning in natural language processing tasks
by: Mei, Taiyuan, et al.
Published: (2024)

An efficient deep reinforcement learning environment for flexible job-shop scheduling
by: Wu, Xinquan, et al.
Published: (2025)

On the consistency of hyper-parameter selection in value-based deep reinforcement learning
by: Obando-Ceron, Johan, et al.
Published: (2024)

Recursive deep learning framework for forecasting the decadal world economic outlook
by: Wang, Tianyi, et al.
Published: (2023)

Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications
by: Mohammadi, Marziyeh, et al.
Published: (2025)

Exploring the design space of deep-learning-based weather forecasting systems
by: Siddiqui, Shoaib Ahmed, et al.
Published: (2024)

Multiplicative update rules for accelerating deep learning training and increasing robustness
by: Kirtas, Manos, et al.
Published: (2023)

A Meta-learning Framework for Tuning Parameters of Protection Mechanisms in Trustworthy Federated Learning
by: Zhang, Xiaojin, et al.
Published: (2023)

Exploring the impact of traffic signal control and connected and automated vehicles on intersections safety: A deep reinforcement learning approach
by: Karbasi, Amir Hossein, et al.
Published: (2024)

Achieving binary weight and activation for LLMs using Post-Training Quantization
by: Song, Siqing, et al.
Published: (2025)

Molecular topological deep learning for polymer property prediction
by: Shen, Cong, et al.
Published: (2024)

Accurate and interpretable drug-drug interaction prediction enabled by knowledge subgraph learning
by: Wang, Yaqing, et al.
Published: (2023)

SCPL: Enhancing Neural Network Training Throughput with Decoupled Local Losses and Model Parallelism
by: Ho, Ming-Yao, et al.
Published: (2026)

Recent advances in deep learning and language models for studying the microbiome
by: Yan, Binghao, et al.
Published: (2024)

bacpipe: a Python package to make bioacoustic deep learning models accessible
by: Kather, Vincent S., et al.
Published: (2026)

Don't throw the baby out with the bathwater: How and why deep learning for ARC
by: Cole, Jack, et al.
Published: (2025)

Synthetic Information towards Maximum Posterior Ratio for deep learning on Imbalanced Data
by: Nguyen, Hung, et al.
Published: (2024)