{"total":181,"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":"2211.08413","title":"Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges","created":"2022-11-15","cited_by_count":138,"area":null},{"id":"2106.05203","title":"EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback","created":"2021-06-09","cited_by_count":133,"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":"2410.01463","title":"Selective Aggregation for Low-Rank Adaptation in Federated Learning","created":"2024-10-02","cited_by_count":80,"area":null},{"id":"2102.07845","title":"MARINA: Faster Non-Convex Distributed Learning with Compression","created":"2021-02-15","cited_by_count":78,"area":null},{"id":"2102.02888","title":"1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed","created":"2021-02-04","cited_by_count":75,"area":null},{"id":"2106.07820","title":"On Large-Cohort Training for Federated Learning","created":"2021-06-15","cited_by_count":74,"area":null},{"id":"2206.00187","title":"DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training","created":"2022-06-01","cited_by_count":74,"area":null},{"id":"2106.04159","title":"Fast Federated Learning in the Presence of Arbitrary Device Unavailability","created":"2021-06-08","cited_by_count":72,"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":"2205.02215","title":"FedNest: Federated Bilevel, Minimax, and Compositional Optimization","created":"2022-05-04","cited_by_count":60,"area":null},{"id":"2205.02719","title":"Communication-Efficient Adaptive Federated Learning","created":"2022-05-05","cited_by_count":55,"area":null},{"id":"2103.05032","title":"Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learning","created":"2021-03-08","cited_by_count":52,"area":null},{"id":"2101.12704","title":"Federated Learning over Wireless Device-to-Device Networks: Algorithms and Convergence Analysis","created":"2021-01-29","cited_by_count":51,"area":null},{"id":"2108.00951","title":"Rethinking gradient sparsification as total error minimization","created":"2021-08-02","cited_by_count":41,"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":"2206.03665","title":"Lower Bounds and Nearly Optimal Algorithms in Distributed Learning with Communication Compression","created":"2022-06-08","cited_by_count":33,"area":null},{"id":"2107.13892","title":"QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning","created":"2021-07-29","cited_by_count":32,"area":"distill"},{"id":"2204.01273","title":"FedSynth: Gradient Compression via Synthetic Data in Federated Learning","created":"2022-04-04","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":"2104.06069","title":"1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed","created":"2021-04-13","cited_by_count":24,"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":"2103.08870","title":"Learned Gradient Compression for Distributed Deep Learning","created":"2021-03-16","cited_by_count":20,"area":null},{"id":"2106.08882","title":"Robust Training in High Dimensions via Block Coordinate Geometric Median Descent","created":"2021-06-16","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":"2212.08343","title":"SplitGP: Achieving Both Generalization and Personalization in Federated Learning","created":"2022-12-16","cited_by_count":20,"area":null},{"id":"2205.05632","title":"On Distributed Adaptive Optimization with Gradient Compression","created":"2022-05-11","cited_by_count":19,"area":null},{"id":"2206.07021","title":"Federated Optimization Algorithms with Random Reshuffling and Gradient Compression","created":"2022-06-14","cited_by_count":18,"area":null},{"id":"2405.17991","title":"VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections","created":"2024-05-28","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":"2205.04180","title":"EF-BV: A Unified Theory of Error Feedback and Variance Reduction Mechanisms for Biased and Unbiased Compression in Distributed Optimization","created":"2022-05-09","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":"2302.02589","title":"$z$-SignFedAvg: A Unified Stochastic Sign-based Compression for Federated Learning","created":"2023-02-06","cited_by_count":17,"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":"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":"2106.03056","title":"MURANA: A Generic Framework for Stochastic Variance-Reduced Optimization","created":"2021-06-06","cited_by_count":14,"area":null},{"id":"2203.04925","title":"Correlated quantization for distributed mean estimation and optimization","created":"2022-03-09","cited_by_count":14,"area":null},{"id":"2305.19442","title":"SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning","created":"2023-05-30","cited_by_count":14,"area":null},{"id":"2307.04942","title":"Benchmarking Algorithms for Federated Domain Generalization","created":"2023-07-11","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":"2106.02797","title":"Neural Distributed Source Coding","created":"2021-06-05","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":"2302.04969","title":"Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative Differentiation","created":"2023-02-09","cited_by_count":13,"area":null},{"id":"2111.00705","title":"Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization","created":"2021-11-01","cited_by_count":12,"area":null},{"id":"2111.07392","title":"Edge-Native Intelligence for 6G Communications Driven by Federated Learning: A Survey of Trends and Challenges","created":"2021-11-14","cited_by_count":12,"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":"2207.08204","title":"Fast Composite Optimization and Statistical Recovery in Federated Learning","created":"2022-07-17","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":"2301.12195","title":"BAFFLE: A Baseline of Backpropagation-Free Federated Learning","created":"2023-01-28","cited_by_count":12,"area":null},{"id":"2310.09804","title":"Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates","created":"2023-10-15","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":"2210.13277","title":"CompressedScaffnew: The First Theoretical Double Acceleration of Communication from Local Training and Compression in Distributed Optimization","created":"2022-10-24","cited_by_count":11,"area":null},{"id":"2210.14396","title":"FeDXL: Provable Federated Learning for Deep X-Risk Optimization","created":"2022-10-26","cited_by_count":11,"area":null},{"id":"2305.07612","title":"Lower Bounds and Accelerated Algorithms in Distributed Stochastic Optimization with Communication Compression","created":"2023-05-12","cited_by_count":11,"area":null},{"id":"2403.04348","title":"LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression","created":"2024-03-07","cited_by_count":11,"area":null},{"id":"2102.12357","title":"Wirelessly Powered Federated Edge Learning: Optimal Tradeoffs Between Convergence and Power Transfer","created":"2021-02-24","cited_by_count":10,"area":null},{"id":"2104.02748","title":"Communication-Efficient Agnostic Federated Averaging","created":"2021-04-06","cited_by_count":10,"area":null},{"id":"2104.12416","title":"Communication-Efficient Federated Learning with Dual-Side Low-Rank Compression","created":"2021-04-26","cited_by_count":10,"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":"2202.02491","title":"Distributed Learning With Sparsified Gradient Differences","created":"2022-02-05","cited_by_count":9,"area":null},{"id":"2205.09868","title":"Service Delay Minimization for Federated Learning over Mobile Devices","created":"2022-05-19","cited_by_count":9,"area":null},{"id":"2312.15186","title":"Efficient Asynchronous Federated Learning with Sparsification and Quantization","created":"2023-12-23","cited_by_count":9,"area":null},{"id":"2112.09355","title":"From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimization","created":"2021-12-17","cited_by_count":8,"area":null},{"id":"2306.03240","title":"Improving Accelerated Federated Learning with Compression and Importance Sampling","created":"2023-06-05","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":"2110.07751","title":"Leveraging Spatial and Temporal Correlations in Sparsified Mean Estimation","created":"2021-10-14","cited_by_count":7,"area":null},{"id":"2202.08420","title":"Time-Correlated Sparsification for Efficient Over-the-Air Model Aggregation in Wireless Federated Learning","created":"2022-02-17","cited_by_count":7,"area":null},{"id":"2205.13341","title":"QUIC-FL: Quick Unbiased Compression for Federated Learning","created":"2022-05-26","cited_by_count":7,"area":null},{"id":"2212.01523","title":"GlueFL: Reconciling Client Sampling and Model Masking for Bandwidth Efficient Federated Learning","created":"2022-12-03","cited_by_count":7,"area":null},{"id":"2301.08869","title":"A Communication-Efficient Adaptive Algorithm for Federated Learning under Cumulative Regret","created":"2023-01-21","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},{"id":"2302.07615","title":"Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities","created":"2023-02-15","cited_by_count":7,"area":null},{"id":"2310.18784","title":"High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise","created":"2023-10-28","cited_by_count":7,"area":null},{"id":"2110.02998","title":"Federated Learning via Plurality Vote","created":"2021-10-06","cited_by_count":6,"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":"2206.10452","title":"Shifted Compression Framework: Generalizations and Improvements","created":"2022-06-21","cited_by_count":6,"area":null},{"id":"2208.07237","title":"Energy and Spectrum Efficient Federated Learning via High-Precision Over-the-Air Computation","created":"2022-08-15","cited_by_count":6,"area":null},{"id":"2209.05148","title":"Personalized Federated Learning with Communication Compression","created":"2022-09-12","cited_by_count":6,"area":null},{"id":"2211.03942","title":"Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design","created":"2022-11-08","cited_by_count":6,"area":null},{"id":"2310.13033","title":"LASER: Linear Compression in Wireless Distributed Optimization","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2312.07060","title":"Layered Randomized Quantization for Communication-Efficient and Privacy-Preserving Distributed Learning","created":"2023-12-12","cited_by_count":6,"area":null},{"id":"2404.10110","title":"Communication-Efficient Hybrid Federated Learning for E-health with Horizontal and Vertical Data Partitioning","created":"2024-04-15","cited_by_count":6,"area":null},{"id":"2105.07829","title":"Compressed Communication for Distributed Training: Adaptive Methods and System","created":"2021-05-17","cited_by_count":5,"area":null},{"id":"2208.06095","title":"A Fast Blockchain-based Federated Learning Framework with Compressed Communications","created":"2022-08-12","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":"2312.15361","title":"Cooperative Federated Learning over Ground-to-Satellite Integrated Networks: Joint Local Computation and Data Offloading","created":"2023-12-23","cited_by_count":5,"area":null},{"id":"2108.13858","title":"GRP-FED: Addressing Client Imbalance in Federated Learning via Global-Regularized Personalization","created":"2021-08-31","cited_by_count":4,"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":"2211.01588","title":"A Convergence Theory for Federated Average: Beyond Smoothness","created":"2022-11-03","cited_by_count":4,"area":null},{"id":"2303.05206","title":"FedREP: A Byzantine-Robust, Communication-Efficient and Privacy-Preserving Framework for Federated Learning","created":"2023-03-09","cited_by_count":4,"area":null},{"id":"2304.13545","title":"Killing Two Birds with One Stone: Quantization Achieves Privacy in Distributed Learning","created":"2023-04-26","cited_by_count":4,"area":null},{"id":"2310.16606","title":"AirFL-Mem: Improving Communication-Learning Trade-Off by Long-Term Memory","created":"2023-10-25","cited_by_count":4,"area":null},{"id":"2410.16871","title":"Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2411.13000","title":"NCAirFL: CSI-Free Over-the-Air Federated Learning Based on Non-Coherent Detection","created":"2024-11-20","cited_by_count":4,"area":null},{"id":"2001.05918","title":"Elastic Consistency: A General Consistency Model for Distributed Stochastic Gradient Descent","created":"2020-01-16","cited_by_count":3,"area":"diffusion"}],"next_cursor":"100"}