Imagen de Portada

Beta-Scheduling: Momentum from Critical Damping as a Diagnostic and Correction Tool for Neural Network Training

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Pasichnyk, Ivan
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

The Yerkes-Dodson Curve for AI Agents: Emergent Cooperation Under Environmental Pressure in Multi-Agent LLM Simulations
por: Pasichnyk, Ivan
Publicado: (2026)

ssProp: Energy-Efficient Training for Convolutional Neural Networks with Scheduled Sparse Back Propagation
por: Zhong, Lujia, et al.
Publicado: (2024)

Momentum-Conserving Graph Neural Networks for Deformable Objects
por: Wang, Jiahong, et al.
Publicado: (2026)

FedMomentum: Preserving LoRA Training Momentum in Federated Fine-Tuning
por: Yan, Peishen, et al.
Publicado: (2026)

Heavy-Ball Momentum Accelerated Actor-Critic With Function Approximation
por: Dong, Yanjie, et al.
Publicado: (2024)

Adaptive Momentum and Nonlinear Damping for Neural Network Training
por: Karoni, Aikaterini, et al.
Publicado: (2026)

On the Occurence of Critical Learning Periods in Neural Networks
por: Pawlak, Stanisław
Publicado: (2025)

Graph Neural Networks for Job Shop Scheduling Problems: A Survey
por: Smit, Igor G., et al.
Publicado: (2024)

Q-Newton: Hybrid Quantum-Classical Scheduling for Accelerating Neural Network Training with Newton's Gradient Descent
por: Li, Pingzhi, et al.
Publicado: (2024)

Are We Measuring Oversmoothing in Graph Neural Networks Correctly?
por: Zhang, Kaicheng, et al.
Publicado: (2025)

Graph-RHO: Critical-path-aware Heterogeneous Graph Network for Long-Horizon Flexible Job-Shop Scheduling
por: Li, Yujie, et al.
Publicado: (2026)

Automatic Stability and Recovery for Neural Network Training
por: Or, Barak
Publicado: (2026)

Training Neural Networks for Modularity aids Interpretability
por: Golechha, Satvik, et al.
Publicado: (2024)

Z-Error Loss for Training Neural Networks
por: Godin, Guillaume
Publicado: (2025)

Gradient-Free Training of Quantized Neural Networks
por: Cohen, Noa, et al.
Publicado: (2024)

Energy Consumption in Parallel Neural Network Training
por: Huber, Philipp, et al.
Publicado: (2025)

Anomaly Detection Based on Critical Paths for Deep Neural Networks
por: Zhao, Fangzhen, et al.
Publicado: (2025)

Symbol Correctness in Deep Neural Networks Containing Symbolic Layers
por: Bembenek, Aaron, et al.
Publicado: (2024)

Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch
por: Zeng, Yirong, et al.
Publicado: (2025)

Harnessing Orthogonality to Train Low-Rank Neural Networks
por: Coquelin, Daniel, et al.
Publicado: (2024)

Dynamic Spectral Backpropagation for Efficient Neural Network Training
por: Muthuraman, Mannmohan
Publicado: (2025)

ROOT: Robust Orthogonalized Optimizer for Neural Network Training
por: He, Wei, et al.
Publicado: (2025)

Explaining Neural Networks without Access to Training Data
por: Marton, Sascha, et al.
Publicado: (2022)

Graph Neural Networks for the Offline Nanosatellite Task Scheduling Problem
por: Pacheco, Bruno Machado, et al.
Publicado: (2023)

Learning to Solve Resource-Constrained Project Scheduling Problems with Duration Uncertainty using Graph Neural Networks
por: Infantes, Guillaume, et al.
Publicado: (2025)

Lightweight Geometric Adaptation for Training Physics-Informed Neural Networks
por: An, Kang, et al.
Publicado: (2026)

Feed-Forward Optimization With Delayed Feedback for Neural Network Training
por: Flügel, Katharina, et al.
Publicado: (2023)

Fast Training of Recurrent Neural Networks with Stationary State Feedbacks
por: Caillon, Paul, et al.
Publicado: (2025)

Training-free Graph Neural Networks and the Power of Labels as Features
por: Sato, Ryoma
Publicado: (2024)

Improved Training of Physics-Informed Neural Networks with Model Ensembles
por: Haitsiukevich, Katsiaryna, et al.
Publicado: (2022)

No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks
por: Refael, Yehonatan, et al.
Publicado: (2025)

Revisiting LARS for Large Batch Training Generalization of Neural Networks
por: Do, Khoi, et al.
Publicado: (2023)

Distillation Enhanced Time Series Forecasting Network with Momentum Contrastive Learning
por: Gao, Haozhi, et al.
Publicado: (2024)

Robust Generalization of Graph Neural Networks for Carrier Scheduling
por: Perez-Ramirez, Daniel F., et al.
Publicado: (2024)

Over-squashing in Spatiotemporal Graph Neural Networks
por: Marisca, Ivan, et al.
Publicado: (2025)

Excitation: Momentum For Experts
por: Shaier, Sagi
Publicado: (2026)

Torque-Aware Momentum
por: Malviya, Pranshu, et al.
Publicado: (2024)

Self-Abstraction Learning for Effective and Stable Training of Deep Neural Networks
por: Cho, Wonyong, et al.
Publicado: (2026)

Enhancing Trustworthiness of Graph Neural Networks with Rank-Based Conformal Training
por: Wang, Ting, et al.
Publicado: (2025)

IDInit: A Universal and Stable Initialization Method for Neural Network Training
por: Pan, Yu, et al.
Publicado: (2025)