{"total":199,"rows":[{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"area":null},{"id":"2103.04628","title":"Personalized Federated Learning using Hypernetworks","created":"2021-03-08","cited_by_count":212,"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":"2106.06639","title":"Federated Learning with Buffered Asynchronous Aggregation","created":"2021-06-11","cited_by_count":190,"area":null},{"id":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134,"area":null},{"id":"2104.02151","title":"Distributed Learning in Wireless Networks: Recent Progress and Future Challenges","created":"2021-04-05","cited_by_count":129,"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":"2105.05883","title":"Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning","created":"2021-05-12","cited_by_count":93,"area":null},{"id":"2106.15482","title":"Personalized Federated Learning with Gaussian Processes","created":"2021-06-29","cited_by_count":76,"area":null},{"id":"2106.07820","title":"On Large-Cohort Training for Federated Learning","created":"2021-06-15","cited_by_count":74,"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":"2403.13101","title":"AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networks","created":"2024-03-19","cited_by_count":64,"area":null},{"id":"2105.13462","title":"On Linear Stability of SGD and Input-Smoothness of Neural Networks","created":"2021-05-27","cited_by_count":63,"area":null},{"id":"2104.04448","title":"Relating Adversarially Robust Generalization to Flat Minima","created":"2021-04-09","cited_by_count":57,"area":null},{"id":"2205.02719","title":"Communication-Efficient Adaptive Federated Learning","created":"2022-05-05","cited_by_count":55,"area":null},{"id":"2211.09299","title":"FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data","created":"2022-11-17","cited_by_count":50,"area":null},{"id":"2102.04828","title":"Consensus Control for Decentralized Deep Learning","created":"2021-02-09","cited_by_count":49,"area":null},{"id":"2110.11027","title":"FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusion","created":"2021-10-21","cited_by_count":49,"area":null},{"id":"2205.13648","title":"A Unified Analysis of Federated Learning with Arbitrary Client Participation","created":"2022-05-26","cited_by_count":45,"area":null},{"id":"2204.10607","title":"Federated Learning via Inexact ADMM","created":"2022-04-22","cited_by_count":44,"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":"2102.13152","title":"Local Stochastic Gradient Descent Ascent: Convergence Analysis and Communication Efficiency","created":"2021-02-25","cited_by_count":40,"area":null},{"id":"2106.09580","title":"Optimality and Stability in Federated Learning: A Game-theoretic Approach","created":"2021-06-17","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":"2111.03741","title":"Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective","created":"2021-11-05","cited_by_count":38,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","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":"2412.07197","title":"Hierarchical Split Federated Learning: Convergence Analysis and System Optimization","created":"2024-12-10","cited_by_count":38,"area":null},{"id":"2103.03239","title":"Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices","created":"2021-03-04","cited_by_count":36,"area":null},{"id":"2206.08330","title":"Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data","created":"2022-06-16","cited_by_count":36,"area":null},{"id":"2205.13462","title":"FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction","created":"2022-05-26","cited_by_count":35,"area":null},{"id":"2301.01313","title":"Decentralized Gradient Tracking with Local Steps","created":"2023-01-03","cited_by_count":32,"area":null},{"id":"2102.03198","title":"Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning","created":"2021-02-05","cited_by_count":31,"area":null},{"id":"2106.02743","title":"SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networks","created":"2021-06-04","cited_by_count":30,"area":null},{"id":"2405.10853","title":"The Future of Large Language Model Pre-training is Federated","created":"2024-05-17","cited_by_count":30,"area":null},{"id":"2103.03452","title":"FedDR -- Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimization","created":"2021-03-05","cited_by_count":29,"area":null},{"id":"2106.13897","title":"Implicit Gradient Alignment in Distributed and Federated Learning","created":"2021-06-25","cited_by_count":29,"area":null},{"id":"2501.18512","title":"Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch","created":"2025-01-30","cited_by_count":28,"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":"2112.13246","title":"Towards Federated Learning on Time-Evolving Heterogeneous Data","created":"2021-12-25","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":"2102.04635","title":"Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity","created":"2021-02-09","cited_by_count":21,"area":null},{"id":"2204.13169","title":"FedShuffle: Recipes for Better Use of Local Work in Federated Learning","created":"2022-04-27","cited_by_count":21,"area":null},{"id":"2210.04757","title":"On the Performance of Gradient Tracking with Local Updates","created":"2022-10-10","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":"2205.05040","title":"A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks","created":"2022-05-10","cited_by_count":20,"area":null},{"id":"2106.04759","title":"Communication-efficient SGD: From Local SGD to One-Shot Averaging","created":"2021-06-09","cited_by_count":19,"area":null},{"id":"2105.11028","title":"Fast Federated Learning by Balancing Communication Trade-Offs","created":"2021-05-23","cited_by_count":18,"area":null},{"id":"2107.00961","title":"ResIST: Layer-Wise Decomposition of ResNets for Distributed Training","created":"2021-07-02","cited_by_count":18,"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":"2111.05897","title":"Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters","created":"2021-11-10","cited_by_count":17,"area":null},{"id":"2306.14853","title":"Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oracles","created":"2023-06-26","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":"2102.01732","title":"Truly Sparse Neural Networks at Scale","created":"2021-02-02","cited_by_count":16,"area":null},{"id":"2105.07806","title":"Towards Demystifying Serverless Machine Learning Training","created":"2021-05-17","cited_by_count":16,"area":null},{"id":"2305.12133","title":"Loss Spike in Training Neural Networks","created":"2023-05-20","cited_by_count":16,"area":null},{"id":"2312.12670","title":"On the Role of Server Momentum in Federated Learning","created":"2023-12-19","cited_by_count":16,"area":null},{"id":"2105.07320","title":"LocalNewton: Reducing Communication Bottleneck for Distributed Learning","created":"2021-05-16","cited_by_count":15,"area":null},{"id":"2202.06009","title":"Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam","created":"2022-02-12","cited_by_count":15,"area":null},{"id":"2301.09830","title":"Optimus-CC: Efficient Large NLP Model Training with 3D Parallelism Aware Communication Compression","created":"2023-01-24","cited_by_count":15,"area":null},{"id":"2301.12379","title":"FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering","created":"2023-01-29","cited_by_count":15,"area":null},{"id":"2506.08426","title":"HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systems","created":"2025-06-10","cited_by_count":15,"area":null},{"id":"2105.01281","title":"Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning with SGX","created":"2021-05-04","cited_by_count":14,"area":null},{"id":"2110.15318","title":"Communication-Efficient ADMM-based Federated Learning","created":"2021-10-28","cited_by_count":14,"area":null},{"id":"2206.05891","title":"Anchor Sampling for Federated Learning with Partial Client Participation","created":"2022-06-13","cited_by_count":14,"area":null},{"id":"2302.03662","title":"Federated Learning with Regularized Client Participation","created":"2023-02-07","cited_by_count":14,"area":null},{"id":"2401.12033","title":"Momentum-SAM: Sharpness Aware Minimization without Computational Overhead","created":"2024-01-22","cited_by_count":14,"area":null},{"id":"2410.15526","title":"SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training","created":"2024-10-20","cited_by_count":14,"area":null},{"id":"2104.06685","title":"BROADCAST: Reducing Both Stochastic and Compression Noise to Robustify Communication-Efficient Federated Learning","created":"2021-04-14","cited_by_count":13,"area":null},{"id":"2107.01499","title":"BAGUA: Scaling up Distributed Learning with System Relaxations","created":"2021-07-03","cited_by_count":13,"area":null},{"id":"2205.03914","title":"Federated Random Reshuffling with Compression and Variance Reduction","created":"2022-05-08","cited_by_count":12,"area":null},{"id":"2208.08490","title":"NET-FLEET: Achieving Linear Convergence Speedup for Fully Decentralized Federated Learning with Heterogeneous Data","created":"2022-08-17","cited_by_count":12,"area":null},{"id":"2212.08496","title":"Federated Learning with Flexible Control","created":"2022-12-16","cited_by_count":12,"area":null},{"id":"2307.07652","title":"DIGEST: Fast and Communication Efficient Decentralized Learning with Local Updates","created":"2023-07-14","cited_by_count":12,"area":null},{"id":"2310.09866","title":"Federated Multi-Objective Learning","created":"2023-10-15","cited_by_count":12,"area":null},{"id":"2405.11667","title":"The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication","created":"2024-05-19","cited_by_count":12,"area":null},{"id":"2411.18607","title":"Task Arithmetic Through The Lens Of One-Shot Federated Learning","created":"2024-11-27","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":"2411.19870","title":"DeMo: Decoupled Momentum Optimization","created":"2024-11-29","cited_by_count":11,"area":null},{"id":"2502.12996","title":"Eager Updates For Overlapped Communication and Computation in DiLoCo","created":"2025-02-18","cited_by_count":11,"area":null},{"id":"2102.10424","title":"GIST: Distributed Training for Large-Scale Graph Convolutional Networks","created":"2021-02-20","cited_by_count":10,"area":null},{"id":"2111.00856","title":"Large-Scale Deep Learning Optimizations: A Comprehensive Survey","created":"2021-11-01","cited_by_count":10,"area":null},{"id":"2210.00690","title":"Taming Fat-Tailed (\"Heavier-Tailed'' with Potentially Infinite Variance) Noise in Federated Learning","created":"2022-10-03","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":"2407.18365","title":"FADAS: Towards Federated Adaptive Asynchronous Optimization","created":"2024-07-25","cited_by_count":10,"area":null},{"id":"2502.01145","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach","created":"2025-02-03","cited_by_count":10,"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":"2509.10439","title":"Understanding Outer Optimizers in Local SGD: Learning Rates, Momentum, and Acceleration","created":"2025-09-12","cited_by_count":9,"area":null},{"id":"2201.03789","title":"Partial Model Averaging in Federated Learning: Performance Guarantees and Benefits","created":"2022-01-11","cited_by_count":8,"area":null},{"id":"2205.01438","title":"FedGiA: An Efficient Hybrid Algorithm for Federated Learning","created":"2022-05-03","cited_by_count":8,"area":null},{"id":"2302.04851","title":"Delay Sensitive Hierarchical Federated Learning with Stochastic Local Updates","created":"2023-02-09","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":"2106.12300","title":"Behavior Mimics Distribution: Combining Individual and Group Behaviors for Federated Learning","created":"2021-06-23","cited_by_count":7,"area":null},{"id":"2109.00534","title":"The Minimax Complexity of Distributed Optimization","created":"2021-09-01","cited_by_count":7,"area":null},{"id":"2302.07155","title":"EPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections for Federated Learning with Heterogeneous Data","created":"2023-02-14","cited_by_count":7,"area":null}],"next_cursor":"100"}