{"total":119,"rows":[{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"area":null},{"id":"2101.11203","title":"Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning","created":"2021-01-27","cited_by_count":193,"area":null},{"id":"2206.02618","title":"Generalized Federated Learning via Sharpness Aware Minimization","created":"2022-06-06","cited_by_count":144,"area":null},{"id":"2311.08105","title":"DiLoCo: Distributed Low-Communication Training of Language Models","created":"2023-11-14","cited_by_count":121,"area":null},{"id":"2308.08165","title":"Stochastic Controlled Averaging for Federated Learning with Communication Compression","created":"2023-08-16","cited_by_count":101,"area":null},{"id":"2106.10874","title":"FedCM: Federated Learning with Client-level Momentum","created":"2021-06-21","cited_by_count":77,"area":null},{"id":"2102.04761","title":"Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data","created":"2021-02-09","cited_by_count":69,"area":null},{"id":"2310.15080","title":"Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization","created":"2023-10-23","cited_by_count":65,"area":null},{"id":"2110.14216","title":"What Do We Mean by Generalization in Federated Learning?","created":"2021-10-27","cited_by_count":62,"area":null},{"id":"2106.10207","title":"Distributed Deep Learning in Open Collaborations","created":"2021-06-18","cited_by_count":58,"area":null},{"id":"2110.13363","title":"Exponential Graph is Provably Efficient for Decentralized Deep Training","created":"2021-10-26","cited_by_count":56,"area":null},{"id":"2205.02719","title":"Communication-Efficient Adaptive Federated Learning","created":"2022-05-05","cited_by_count":55,"area":null},{"id":"2409.03137","title":"The AdEMAMix Optimizer: Better, Faster, Older","created":"2024-09-05","cited_by_count":54,"area":null},{"id":"2102.04828","title":"Consensus Control for Decentralized Deep Learning","created":"2021-02-09","cited_by_count":49,"area":null},{"id":"2302.10429","title":"FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy","created":"2023-02-21","cited_by_count":49,"area":null},{"id":"2305.11584","title":"Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape","created":"2023-05-19","cited_by_count":46,"area":null},{"id":"2106.01432","title":"SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Training","created":"2021-06-02","cited_by_count":45,"area":null},{"id":"2106.10435","title":"STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning","created":"2021-06-19","cited_by_count":43,"area":null},{"id":"2104.11981","title":"DecentLaM: Decentralized Momentum SGD for Large-batch Deep Training","created":"2021-04-24","cited_by_count":40,"area":null},{"id":"2205.10920","title":"Test-Time Robust Personalization for Federated Learning","created":"2022-05-22","cited_by_count":39,"area":null},{"id":"2206.04723","title":"On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data","created":"2022-06-09","cited_by_count":38,"area":null},{"id":"2306.16504","title":"Momentum Benefits Non-IID Federated Learning Simply and Provably","created":"2023-06-28","cited_by_count":38,"area":null},{"id":"2103.02051","title":"Cross-Gradient Aggregation for Decentralized Learning from Non-IID data","created":"2021-03-02","cited_by_count":33,"area":null},{"id":"2106.02305","title":"Local Adaptivity in Federated Learning: Convergence and Consistency","created":"2021-06-04","cited_by_count":31,"area":null},{"id":"2302.03109","title":"On the Convergence of Federated Averaging with Cyclic Client Participation","created":"2023-02-06","cited_by_count":31,"area":null},{"id":"2101.08837","title":"Time-Correlated Sparsification for Communication-Efficient Federated Learning","created":"2021-01-21","cited_by_count":26,"area":null},{"id":"2207.06343","title":"TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2401.09135","title":"Asynchronous Local-SGD Training for Language Modeling","created":"2024-01-17","cited_by_count":26,"area":null},{"id":"2105.09080","title":"Accelerating Gossip SGD with Periodic Global Averaging","created":"2021-05-19","cited_by_count":25,"area":null},{"id":"2201.03172","title":"Communication-Efficient Federated Learning with Accelerated Client Gradient","created":"2022-01-10","cited_by_count":24,"area":null},{"id":"2207.07223","title":"Accelerated Federated Learning with Decoupled Adaptive Optimization","created":"2022-07-14","cited_by_count":23,"area":null},{"id":"2308.00522","title":"Efficient Federated Learning via Local Adaptive Amended Optimizer with Linear Speedup","created":"2023-07-30","cited_by_count":23,"area":null},{"id":"2204.13170","title":"AdaBest: Minimizing Client Drift in Federated Learning via Adaptive Bias Estimation","created":"2022-04-27","cited_by_count":21,"area":null},{"id":"2306.05706","title":"Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization","created":"2023-06-09","cited_by_count":21,"area":null},{"id":"2110.08133","title":"Trade-offs of Local SGD at Scale: An Empirical Study","created":"2021-10-15","cited_by_count":20,"area":null},{"id":"2205.01608","title":"Local Stochastic Bilevel Optimization with Momentum-Based Variance Reduction","created":"2022-05-03","cited_by_count":20,"area":null},{"id":"2209.15505","title":"Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data","created":"2022-09-30","cited_by_count":20,"area":null},{"id":"2505.23725","title":"MuLoCo: Muon is a practical inner optimizer for DiLoCo","created":"2025-05-29","cited_by_count":18,"area":null},{"id":"2110.12347","title":"Acceleration in Distributed Optimization under Similarity","created":"2021-10-24","cited_by_count":17,"area":null},{"id":"2206.10189","title":"A General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updates","created":"2022-06-21","cited_by_count":17,"area":null},{"id":"2401.16265","title":"CO2: Efficient Distributed Training with Full Communication-Computation Overlap","created":"2024-01-29","cited_by_count":17,"area":null},{"id":"2402.16828","title":"Training Neural Networks from Scratch with Parallel Low-Rank Adapters","created":"2024-02-26","cited_by_count":17,"area":null},{"id":"2202.00280","title":"Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank?","created":"2022-02-01","cited_by_count":16,"area":null},{"id":"2106.11257","title":"Secure Distributed Training at Scale","created":"2021-06-21","cited_by_count":12,"area":null},{"id":"2106.11264","title":"Compositional federated learning: Applications in distributionally robust averaging and meta learning","created":"2021-06-21","cited_by_count":12,"area":null},{"id":"2508.15706","title":"Overcoming the Communication-Performance Tradeoff in LLM Pretraining","created":"2025-08-21","cited_by_count":12,"area":null},{"id":"2108.06869","title":"FedChain: Chained Algorithms for Near-Optimal Communication Cost in Federated Learning","created":"2021-08-16","cited_by_count":11,"area":null},{"id":"2211.12578","title":"Online Federated Learning via Non-Stationary Detection and Adaptation amidst Concept Drift","created":"2022-11-22","cited_by_count":10,"area":null},{"id":"2404.06114","title":"Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey","created":"2024-04-09","cited_by_count":10,"area":null},{"id":"2406.01116","title":"Accelerating Heterogeneous Federated Learning with Closed-form Classifiers","created":"2024-06-03","cited_by_count":10,"area":null},{"id":"2102.03970","title":"Coordinating Momenta for Cross-silo Federated Learning","created":"2021-02-08","cited_by_count":9,"area":null},{"id":"2105.02501","title":"Federated Face Recognition","created":"2021-05-06","cited_by_count":9,"area":null},{"id":"2109.03999","title":"Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies","created":"2021-09-09","cited_by_count":9,"area":null},{"id":"2206.06257","title":"Distributed Adversarial Training to Robustify Deep Neural Networks at Scale","created":"2022-06-13","cited_by_count":9,"area":null},{"id":"2405.17517","title":"WASH: Train your Ensemble with Communication-Efficient Weight Shuffling, then Average","created":"2024-05-27","cited_by_count":9,"area":null},{"id":"2107.12211","title":"A General Theory for Client Sampling in Federated Learning","created":"2021-07-26","cited_by_count":8,"area":null},{"id":"2208.09894","title":"Byzantines can also Learn from History: Fall of Centered Clipping in Federated Learning","created":"2022-08-21","cited_by_count":8,"area":null},{"id":"2209.07116","title":"On Generalization of Decentralized Learning with Separable Data","created":"2022-09-15","cited_by_count":8,"area":null},{"id":"2301.09357","title":"Accelerating Fair Federated Learning: Adaptive Federated Adam","created":"2023-01-23","cited_by_count":8,"area":null},{"id":"2308.04077","title":"Federated Zeroth-Order Optimization using Trajectory-Informed Surrogate Gradients","created":"2023-08-08","cited_by_count":8,"area":null},{"id":"2410.18478","title":"Classifier Clustering and Feature Alignment for Federated Learning under Distributed Concept Drift","created":"2024-10-24","cited_by_count":8,"area":null},{"id":"2510.15830","title":"SNOO: Step-K Nesterov Outer Optimizer - The Surprising Effectiveness of Nesterov Momentum Applied to Pseudo-Gradients","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2106.07155","title":"CFedAvg: Achieving Efficient Communication and Fast Convergence in Non-IID Federated Learning","created":"2021-06-14","cited_by_count":7,"area":null},{"id":"2310.01366","title":"Window-based Model Averaging Improves Generalization in Heterogeneous Federated Learning","created":"2023-10-02","cited_by_count":7,"area":null},{"id":"2502.19717","title":"Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2206.04742","title":"Accelerating Asynchronous Federated Learning Convergence via Opportunistic Mobile Relaying","created":"2022-06-09","cited_by_count":6,"area":null},{"id":"2210.14560","title":"Hierarchical Federated Learning with Momentum Acceleration in Multi-Tier Networks","created":"2022-10-26","cited_by_count":6,"area":null},{"id":"2406.02613","title":"ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2408.05678","title":"Efficient Federated Learning Using Dynamic Update and Adaptive Pruning with Momentum on Shared Server Data","created":"2024-08-11","cited_by_count":6,"area":null},{"id":"2202.11850","title":"Robust Federated Learning with Connectivity Failures: A Semi-Decentralized Framework with Collaborative Relaying","created":"2022-02-24","cited_by_count":5,"area":null},{"id":"2310.05093","title":"Asymmetrically Decentralized Federated Learning","created":"2023-10-08","cited_by_count":5,"area":null},{"id":"2310.14423","title":"A Quadratic Synchronization Rule for Distributed Deep Learning","created":"2023-10-22","cited_by_count":5,"area":null},{"id":"2405.20114","title":"Towards Faster Decentralized Stochastic Optimization with Communication Compression","created":"2024-05-30","cited_by_count":5,"area":null},{"id":"2407.19234","title":"Ordered Momentum for Asynchronous SGD","created":"2024-07-27","cited_by_count":5,"area":null},{"id":"2112.05559","title":"Collaborative Learning over Wireless Networks: An Introductory Overview","created":"2021-12-07","cited_by_count":4,"area":null},{"id":"2306.10598","title":"DropCompute: simple and more robust distributed synchronous training via compute variance reduction","created":"2023-06-18","cited_by_count":4,"area":null},{"id":"2309.06692","title":"Tackling the Non-IID Issue in Heterogeneous Federated Learning by Gradient Harmonization","created":"2023-09-13","cited_by_count":4,"area":null},{"id":"2407.15567","title":"A New Theoretical Perspective on Data Heterogeneity in Federated Optimization","created":"2024-07-22","cited_by_count":4,"area":null},{"id":"2410.11998","title":"From promise to practice: realizing high-performance decentralized training","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2410.13743","title":"Single-Timescale Multi-Sequence Stochastic Approximation Without Fixed Point Smoothness: Theories and Applications","created":"2024-10-17","cited_by_count":4,"area":null},{"id":"2110.00532","title":"Layer-wise and Dimension-wise Locally Adaptive Federated Learning","created":"2021-10-01","cited_by_count":3,"area":null},{"id":"2306.03747","title":"Towards Scalable Multi-View Reconstruction of Geometry and Materials","created":"2023-06-06","cited_by_count":3,"area":null},{"id":"2308.11646","title":"Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Data","created":"2023-08-17","cited_by_count":3,"area":null},{"id":"2402.09247","title":"Momentum Approximation in Asynchronous Private Federated Learning","created":"2024-02-14","cited_by_count":3,"area":null},{"id":"2412.01630","title":"Review of Mathematical Optimization in Federated Learning","created":"2024-12-02","cited_by_count":3,"area":null},{"id":"2207.08391","title":"Federated Learning for Non-IID Data via Client Variance Reduction and Adaptive Server Update","created":"2022-07-18","cited_by_count":2,"area":null},{"id":"2209.10537","title":"FedFOR: Stateless Heterogeneous Federated Learning with First-Order Regularization","created":"2022-09-21","cited_by_count":2,"area":null},{"id":"2308.13157","title":"Federated Learning in IoT: a Survey from a Resource-Constrained Perspective","created":"2023-08-25","cited_by_count":2,"area":null},{"id":"2309.09719","title":"FedLALR: Client-Specific Adaptive Learning Rates Achieve Linear Speedup for Non-IID Data","created":"2023-09-18","cited_by_count":2,"area":null},{"id":"2312.02204","title":"Meta-learning Optimizers for Communication-Efficient Learning","created":"2023-12-02","cited_by_count":2,"area":null},{"id":"2409.18915","title":"A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needs","created":"2024-09-27","cited_by_count":2,"area":null},{"id":"2304.10744","title":"Joint Client Assignment and UAV Route Planning for Indirect-Communication Federated Learning","created":"2023-04-21","cited_by_count":1,"area":null},{"id":"2405.11389","title":"Adjacent Leader Decentralized Stochastic Gradient Descent","created":"2024-05-18","cited_by_count":1,"area":null},{"id":"2406.00846","title":"Local Methods with Adaptivity via Scaling","created":"2024-06-02","cited_by_count":1,"area":null},{"id":"2411.17866","title":"Distributed Sign Momentum with Local Steps for Training Transformers","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2507.14980","title":"FedWCM: Unleashing the Potential of Momentum-based Federated Learning in Long-Tailed Scenarios","created":"2025-07-20","cited_by_count":1,"area":null},{"id":"2509.22418","title":"Partial Parameter Updates for Efficient Distributed Training","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2606.11081","title":"Unifying Local Communications and Local Updates for LLM Pretraining","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2108.02517","title":"Multi-task Federated Edge Learning (MtFEEL) in Wireless Networks","created":"2021-08-05","cited_by_count":0,"area":null},{"id":"2209.12307","title":"On the Stability Analysis of Open Federated Learning Systems","created":"2022-09-25","cited_by_count":0,"area":null}],"next_cursor":"100"}