Image de couverture de livre

Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Qinglun, Liu, Yingqi, Zhang, Miao, Cao, Xiaochun, Yin, Quanjun, Shen, Li
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Numerical Analysis
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

OledFL: Unleashing the Potential of Decentralized Federated Learning via Opposite Lookahead Enhancement
par: Li, Qinglun, et autres
Publié: (2024)

Boosting the Performance of Decentralized Federated Learning via Catalyst Acceleration
par: Li, Qinglun, et autres
Publié: (2024)

Characteristic Learning for Provable One Step Generation
par: Ding, Zhao, et autres
Publié: (2024)

Core-Halo Decomposition: Decentralizing Large-Scale Fixed-Point Problems
par: Haixiang, et autres
Publié: (2026)

Training Stiff Neural Ordinary Differential Equations with Implicit Single-Step Methods
par: Fronk, Colby, et autres
Publié: (2024)

Online Pseudo-average Shifting Attention(PASA) for Robust Low-precision LLM Inference: Algorithms and Numerical Analysis
par: Cheng, Long, et autres
Publié: (2025)

V-ABFT: Variance-Based Adaptive Threshold for Fault-Tolerant Matrix Multiplication in Mixed-Precision Deep Learning
par: Gao, Yiheng, et autres
Publié: (2026)

AI Assistants to Enhance and Exploit the PETSc Knowledge Base
par: Smith, Barry, et autres
Publié: (2025)

Dominance Based Crossover Operator for Evolutionary Multi-objective Algorithms
par: Roudenko, Olga, et autres
Publié: (2005)

RMFlow: Refined Mean Flow by a Noise-Injection Step for Multimodal Generation
par: Huang, Yuhao, et autres
Publié: (2026)

Branching Strategies Based on Subgraph GNNs: A Study on Theoretical Promise versus Practical Reality
par: Zhou, Junru, et autres
Publié: (2025)

Mitigating spectral bias for the multiscale operator learning
par: Liu, Xinliang, et autres
Publié: (2022)

Bayesian Interpolating Neural Network (B-INN): a scalable and reliable Bayesian model for large-scale physical systems
par: Park, Chanwook, et autres
Publié: (2026)

Market-Driven Subset Selection for Budgeted Training
par: Jha, Ashish, et autres
Publié: (2025)

SymMaP: Improving Computational Efficiency in Linear Solvers through Symbolic Preconditioning
par: Wang, Hong, et autres
Publié: (2025)

Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling
par: Wang, Hong, et autres
Publié: (2024)

UGM2N: An Unsupervised and Generalizable Mesh Movement Network via M-Uniform Loss
par: Wang, Zhichao, et autres
Publié: (2025)

MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation
par: Wang, Qi, et autres
Publié: (2025)

PowerStep: Memory-Efficient Adaptive Optimization via $\ell_p$-Norm Steepest Descent
par: Lu, Yao, et autres
Publié: (2026)

CodePDE: An Inference Framework for LLM-driven PDE Solver Generation
par: Li, Shanda, et autres
Publié: (2025)

PDE Generalization of In-Context Operator Networks: A Study on 1D Scalar Nonlinear Conservation Laws
par: Yang, Liu, et autres
Publié: (2024)

A Mathematical Explanation of Transformers
par: Tai, Xue-Cheng, et autres
Publié: (2025)

DeepContour: A Hybrid Deep Learning Framework for Accelerating Generalized Eigenvalue Problem Solving via Efficient Contour Design
par: Chen, Yeqiu, et autres
Publié: (2025)

ELM-DeepONets: Backpropagation-Free Training of Deep Operator Networks via Extreme Learning Machines
par: Son, Hwijae
Publié: (2025)

AlgoFormer: An Efficient Transformer Framework with Algorithmic Structures
par: Gao, Yihang, et autres
Publié: (2024)

Data-Efficient Neural Operator Training via Physics-Based Active Learning
par: Polanska, Alicja, et autres
Publié: (2026)

Intrinsic and Extrinsic Organized Attention: Softmax Invariance and Network Sparsity
par: Fasina, Oluwadamilola, et autres
Publié: (2025)

On the Well-Posedness of Green's Function Reconstruction via the Kirchhoff-Helmholtz Equation for One-Speed Neutron Diffusion
par: Ponciroli, Roberto
Publié: (2025)

ODE-DPS: ODE-based Diffusion Posterior Sampling for Inverse Problems in Partial Differential Equation
par: Jiang, Enze, et autres
Publié: (2024)

Fast convolution algorithm for state space models
par: Beylkin, Gregory
Publié: (2024)

Can ChatGPT implement finite element models for geotechnical engineering applications?
par: Kim, Taegu, et autres
Publié: (2025)

Using Crank-Nikolson Scheme to Solve the Korteweg-de Vries (KdV) Equation
par: Wu, Qiming
Publié: (2024)

A hybrid FEM-PINN method for time-dependent partial differential equations
par: Feng, Xiaodong, et autres
Publié: (2024)

Stable Weight Updating: A Key to Reliable PDE Solutions Using Deep Learning
par: Noorizadegan, A., et autres
Publié: (2024)

A data-driven learned discretization approach in finite volume schemes for hyperbolic conservation laws and varying boundary conditions
par: de Romémont, Guillaume, et autres
Publié: (2024)

Uncertain but Useful: Leveraging CNN Variability into Data Augmentation
par: Gonzalez-Pepe, Inés, et autres
Publié: (2025)

Improved Monte Carlo tree search formulation with multiple root nodes for discrete sizing optimization of truss structures
par: Ko, Fu-Yao, et autres
Publié: (2023)

Neural Multigrid Architectures
par: Fanaskov, Vladimir
Publié: (2024)

Robust Physics-Guided Diffusion for Full-Waveform Inversion
par: Peng, Jishen, et autres
Publié: (2026)

Enhancing Forex Forecasting Accuracy: The Impact of Hybrid Variable Sets in Cognitive Algorithmic Trading Systems
par: King, Juan C., et autres
Publié: (2025)