Image de couverture de livre

Can We Theoretically Quantify the Impacts of Local Updates on the Generalization Performance of Federated Learning?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ju, Peizhong, Yang, Haibo, Liu, Jia, Liang, Yingbin, Shroff, Ness
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers
par: Liang, Yuchen, et autres
Publié: (2024)

Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach
par: Liang, Yuchen, et autres
Publié: (2024)

Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective
par: Deng, Junze, et autres
Publié: (2025)

Provable Last-Iterate Convergence for Multi-Objective Safe LLM Alignment via Optimistic Primal-Dual
par: Li, Yining, et autres
Publié: (2026)

How to Find the Exact Pareto Front for Multi-Objective MDPs?
par: Li, Yining, et autres
Publié: (2024)

From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models
par: Liang, Yuchen, et autres
Publié: (2026)

BeST -- A Novel Source Selection Metric for Transfer Learning
par: Soni, Ashutosh, et autres
Publié: (2025)

Mixture-of-Transformers Learn Faster: A Theoretical Study on Classification Problems
par: Li, Hongbo, et autres
Publié: (2025)

Near-Optimal Partially Observable Reinforcement Learning with Partial Online State Information
par: Shi, Ming, et autres
Publié: (2023)

An LP-based Sampling Policy for Multi-Armed Bandits with Side-Observations and Stochastic Availability
par: Soni, Ashutosh, et autres
Publié: (2026)

AI‐EDGE: An NSF AI institute for future edge networks and distributed intelligence
par: Peizhong Ju, et autres
Publié: (2024)

Sharp Convergence Rates for Masked Diffusion Models
par: Liang, Yuchen, et autres
Publié: (2026)

Monitoring State Transitions in Markovian Systems with Sampling Cost
par: Saurav, Kumar, et autres
Publié: (2025)

Regret Bounds for Reinforcement Learning from Multi-Source Imperfect Preferences
par: Shi, Ming, et autres
Publié: (2026)

Discrete Diffusion Models: Novel Analysis and New Sampler Guarantees
par: Liang, Yuchen, et autres
Publié: (2025)

Theory on Mixture-of-Experts in Continual Learning
par: Li, Hongbo, et autres
Publié: (2024)

Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models
par: Liang, Yuchen, et autres
Publié: (2025)

PSMGD: Periodic Stochastic Multi-Gradient Descent for Fast Multi-Objective Optimization
par: Xu, Mingjing, et autres
Publié: (2024)

Learnable Chernoff Baselines for Inference-Time Alignment
par: Madhow, Sunil, et autres
Publié: (2026)

Constraint-Rectified Training for Efficient Chain-of-Thought
par: Wu, Qinhang, et autres
Publié: (2026)

FIRM: Federated In-client Regularized Multi-objective Alignment for Large Language Models
par: Nourzad, Fatemeh, et autres
Publié: (2025)

Prediction-Assisted Online Distributed Deep Learning Workload Scheduling in GPU Clusters
par: Luo, Ziyue, et autres
Publié: (2025)

Flow Matching for Offline Reinforcement Learning with Discrete Actions
par: Khan, Fairoz Nower, et autres
Publié: (2026)

FSL-SAGE: Accelerating Federated Split Learning via Smashed Activation Gradient Estimation
par: Nair, Srijith, et autres
Publié: (2025)

GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data
par: Zhang, Jifan, et autres
Publié: (2024)

Optimal Parallel Scheduling under Concave Speedup Functions
par: Li, Chengzhang, et autres
Publié: (2025)

How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias
par: Huang, Ruiquan, et autres
Publié: (2025)

Provably Efficient Multi-Objective Bandit Algorithms under Preference-Centric Customization
par: Cao, Linfeng, et autres
Publié: (2025)

Beyond Freshness and Semantics: A Coupon-Collector Framework for Effective Status Updates
par: Ahmed, Youssef, et autres
Publié: (2026)

Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates
par: Allouah, Youssef, et autres
Publié: (2024)

A Theoretical Analysis of Self-Supervised Learning for Vision Transformers
par: Huang, Yu, et autres
Publié: (2024)

Escaping Offline Pessimism: Vector-Field Reward Shaping for Safe Frontier Exploration
par: Roknilamouki, Amirhossein, et autres
Publié: (2026)

Discrete Flow Matching for Offline-to-Online Reinforcement Learning
par: Khan, Fairoz Nower, et autres
Publié: (2026)

Exploring the Impact of Parameter Update Magnitude on Forgetting and Generalization of Continual Learning
par: He, JinLi, et autres
Publié: (2026)

Robust Offline Reinforcement Learning for Non-Markovian Decision Processes
par: Huang, Ruiquan, et autres
Publié: (2024)

Provably Efficient UCB-type Algorithms For Learning Predictive State Representations
par: Huang, Ruiquan, et autres
Publié: (2023)

Towards Straggler-Resilient Split Federated Learning: An Unbalanced Update Approach
par: Liang, Dandan, et autres
Publié: (2025)

Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails
par: Jin, Ruinan, et autres
Publié: (2026)

Optimized Local Updates in Federated Learning via Reinforcement Learning
par: Murad, Ali, et autres
Publié: (2025)

Sparse Mixture-of-Experts for Compositional Generalization: Empirical Evidence and Theoretical Foundations of Optimal Sparsity
par: Zhao, Jinze, et autres
Publié: (2024)