Imagen de Portada

Dynamic Momentum Recalibration in Online Gradient Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yao, Zhipeng, Yu, Rui, Chang, Guisong, Li, Ying, Zhang, Yu, Li, Dazhou
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Signal Processing Meets SGD: From Momentum to Filter
por: Yao, Zhipeng, et al.
Publicado: (2023)

Elucidating Representation Degradation Problem in Diffusion Model Training
por: Yao, Zhipeng, et al.
Publicado: (2026)

PolyhedronNet: Representation Learning for Polyhedra with Surface-attributed Graph
por: Yu, Dazhou, et al.
Publicado: (2025)

Self-consistent Deep Geometric Learning for Heterogeneous Multi-source Spatial Point Data Prediction
por: Yu, Dazhou, et al.
Publicado: (2024)

PolygonGNN: Representation Learning for Polygonal Geometries with Heterogeneous Visibility Graph
por: Yu, Dazhou, et al.
Publicado: (2024)

UDQL: Bridging The Gap between MSE Loss and The Optimal Value Function in Offline Reinforcement Learning
por: Zhang, Yu, et al.
Publicado: (2024)

Stochastic Normalized Gradient Descent with Momentum for Large-Batch Training
por: Zhao, Shen-Yi, et al.
Publicado: (2020)

Dynamic Allocation Hypernetwork with Adaptive Model Recalibration for Federated Continual Learning
por: Qi, Xiaoming, et al.
Publicado: (2025)

Fast Stochastic Policy Gradient: Negative Momentum for Reinforcement Learning
por: Zhang, Haobin, et al.
Publicado: (2024)

Dynamic Allocation Hypernetwork with Adaptive Model Recalibration for FCL
por: Qi, Xiaoming, et al.
Publicado: (2025)

Perceive, Route and Modulate: Dynamic Pattern Recalibration for Time Series Forecasting
por: Zhong, Siru, et al.
Publicado: (2026)

Measuring Learning Progress via Gradient-Momentum Coupling
por: Blad, Samuel, et al.
Publicado: (2026)

Ordered Momentum for Asynchronous SGD
por: Shi, Chang-Wei, et al.
Publicado: (2024)

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

BP(λ): Online Learning via Synthetic Gradients
por: Pemberton, Joseph, et al.
Publicado: (2024)

Online Statistical Inference for Contextual Bandits via Stochastic Gradient Descent
por: Chang, Xiangyu, et al.
Publicado: (2022)

Transferable Unsupervised Outlier Detection Framework for Human Semantic Trajectories
por: Zhang, Zheng, et al.
Publicado: (2024)

HOME-3: High-Order Momentum Estimator with Third-Power Gradient for Convex and Smooth Nonconvex Optimization
por: Zhang, Wei, et al.
Publicado: (2025)

On the Generalization of Stochastic Gradient Descent with Momentum
por: Ramezani-Kebrya, Ali, et al.
Publicado: (2018)

Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning
por: Lin, Haoxin, et al.
Publicado: (2024)

Ordered Local Momentum for Asynchronous Distributed Learning under Arbitrary Delays
por: Shi, Chang-Wei, et al.
Publicado: (2026)

Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach
por: Yan, Yu-Hu, et al.
Publicado: (2023)

Accelerated Policy Gradient: On the Convergence Rates of the Nesterov Momentum for Reinforcement Learning
por: Chen, Yen-Ju, et al.
Publicado: (2023)

Global Momentum Compression for Sparse Communication in Distributed Learning
por: Shi, Chang-Wei, et al.
Publicado: (2019)

Momentum Approximation in Asynchronous Private Federated Learning
por: Yu, Tao, et al.
Publicado: (2024)

Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers
por: Yan, Kai, et al.
Publicado: (2024)

Building Gradient Bridges: Label Leakage from Restricted Gradient Sharing in Federated Learning
por: Zhang, Rui, et al.
Publicado: (2024)

Few-Shot Recalibration of Language Models
por: Li, Xiang Lisa, et al.
Publicado: (2024)

Rethinking Momentum Knowledge Distillation in Online Continual Learning
por: Michel, Nicolas, et al.
Publicado: (2023)

Bayesian Online Natural Gradient (BONG)
por: Jones, Matt, et al.
Publicado: (2024)

Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum
por: Zhou, Yuan, et al.
Publicado: (2025)

Rapid Learning in Constrained Minimax Games with Negative Momentum
por: Fang, Zijian, et al.
Publicado: (2024)

PAC-Bayes Analysis for Recalibration in Classification
por: Fujisawa, Masahiro, et al.
Publicado: (2024)

Limited Memory Online Gradient Descent for Kernelized Pairwise Learning with Dynamic Averaging
por: AlQuabeh, Hilal, et al.
Publicado: (2024)

Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability
por: Zhang, Yu-Jie, et al.
Publicado: (2025)

Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics
por: Zhang, Xinyu, et al.
Publicado: (2024)

Parallel Momentum Methods Under Biased Gradient Estimations
por: Beikmohammadi, Ali, et al.
Publicado: (2024)

Grams: Gradient Descent with Adaptive Momentum Scaling
por: Cao, Yang, et al.
Publicado: (2024)

Semantic Communication-Enhanced Split Federated Learning for Vehicular Networks: Architecture, Challenges, and Case Study
por: Yu, Lu, et al.
Publicado: (2026)

Global Convergence of Wasserstein Policy Gradient for Entropy-Regularized Reinforcement Learning
por: Zhu, Zhaoyu, et al.
Publicado: (2026)