Cover Image

Why Federated Optimization Fails to Achieve Perfect Fitting? A Theoretical Perspective on Client-Side Optima

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lei, Zhongxiang, Yang, Qi, Qiu, Ping, Zhang, Gang, Ma, Yuanchi, Liu, Jinyan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FedZMG: Efficient Client-Side Optimization in Federated Learning
by: Zantalis, Fotios, et al.
Published: (2026)

Long text outline generation: Chinese text outline based on unsupervised framework and large language mode
by: Yan, Yan, et al.
Published: (2024)

Why Retrieval-Augmented Generation Fails: A Graph Perspective
by: Guo, Kai, et al.
Published: (2026)

Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
by: Qiu, Haiquan, et al.
Published: (2025)

Client-Side Patching against Backdoor Attacks in Federated Learning
by: Molina-Coronado, Borja
Published: (2024)

Why Retrying Fails: Context Contamination in LLM Agent Pipelines
by: Yang, Zhanfu
Published: (2026)

Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System
by: Chen, Weize, et al.
Published: (2024)

One Step to the Side: Why Defenses Against Malicious Finetuning Fail Under Adaptive Adversaries
by: Zloczower, Itay, et al.
Published: (2026)

Why Do Multi-Agent LLM Systems Fail?
by: Cemri, Mert, et al.
Published: (2025)

AI Achieves a Perfect LSAT Score
by: Ku, Bonmu
Published: (2026)

An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning
by: Zhang, Jianqing, et al.
Published: (2024)

Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective
by: Aghzal, Mohamed, et al.
Published: (2026)

Client-Centric Federated Adaptive Optimization
by: Sun, Jianhui, et al.
Published: (2025)

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond
by: Ke, Yekun, et al.
Published: (2024)

Why Chain of Thought Fails in Clinical Text Understanding
by: Wu, Jiageng, et al.
Published: (2025)

Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards
by: Wu, Shirley, et al.
Published: (2025)

Why Rectified Power Unit Networks Fail and How to Improve It: An Effective Field Theory Perspective
by: Kim, Taeyoung, et al.
Published: (2024)

Subfunction Structure Matters: A New Perspective on Local Optima Networks
by: Thomson, S. L., et al.
Published: (2025)

Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models
by: Nguyen, Quan, et al.
Published: (2025)

The Keyhole Effect: Why Chat Interfaces Fail at Data Analysis
by: Reddy, Mohan
Published: (2026)

Perspective Transition of Large Language Models for Solving Subjective Tasks
by: Wang, Xiaolong, et al.
Published: (2025)

FilFL: Client Filtering for Optimized Client Participation in Federated Learning
by: Fourati, Fares, et al.
Published: (2023)

Tackling Noisy Clients in Federated Learning with End-to-end Label Correction
by: Jiang, Xuefeng, et al.
Published: (2024)

FedPOB: Sample-Efficient Federated Prompt Optimization via Bandits
by: Lu, Pingchen, et al.
Published: (2025)

Local Optima in Diversity Optimization: Non-trivial Offspring Population is Essential
by: Antipov, Denis, et al.
Published: (2024)

Robust Federated Learning against Noisy Clients via Masked Optimization
by: Jiang, Xuefeng, et al.
Published: (2025)

WebSuite: Systematically Evaluating Why Web Agents Fail
by: Li, Eric, et al.
Published: (2024)

The Defense Trilemma: Why Prompt Injection Defense Wrappers Fail?
by: Bhatt, Manish, et al.
Published: (2026)

Why Do Transformers Fail to Forecast Time Series In-Context?
by: Zhou, Yufa, et al.
Published: (2025)

FedFiTS: Fitness-Selected, Slotted Client Scheduling for Trustworthy Federated Learning in Healthcare AI
by: Kahenga, Ferdinand, et al.
Published: (2025)

Optimizing Federated Learning by Entropy-Based Client Selection
by: Lutz, Andreas, et al.
Published: (2024)

FedConv: A Learning-on-Model Paradigm for Heterogeneous Federated Clients
by: Shen, Leming, et al.
Published: (2025)

Why LLMs Fail at Causal Discovery and How Interventional Agents Escape
by: Roy, Amartya, et al.
Published: (2026)

Consensus is Not Verification: Why Crowd Wisdom Strategies Fail for LLM Truthfulness
by: Denisov-Blanch, Yegor, et al.
Published: (2026)

Towards Achieving Perfect Multimodal Alignment
by: Kamboj, Abhi, et al.
Published: (2025)

Galton's Law of Mediocrity: Why Large Language Models Regress to the Mean and Fail at Creativity in Advertising
by: Keon, Matt, et al.
Published: (2025)

The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective
by: Zhu, Guogang, et al.
Published: (2025)

Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine
by: Wu, Yuan, et al.
Published: (2026)

Federated Linear Contextual Bandits with Heterogeneous Clients
by: Blaser, Ethan, et al.
Published: (2024)

Why Attention Fails: A Taxonomy of Faults in Attention-Based Neural Networks
by: Jahan, Sigma, et al.
Published: (2025)