{"total":122,"rows":[{"id":"2108.10252","title":"Federated Multi-Task Learning under a Mixture of Distributions","created":"2021-08-23","cited_by_count":192,"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":"2306.01603","title":"Decentralized Federated Learning: A Survey and Perspective","created":"2023-06-02","cited_by_count":86,"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":"2202.03836","title":"An Improved Analysis of Gradient Tracking for Decentralized Machine Learning","created":"2022-02-08","cited_by_count":69,"area":null},{"id":"2111.11343","title":"Decentralized Federated Learning through Proxy Model Sharing","created":"2021-11-22","cited_by_count":57,"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":"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":"2201.13320","title":"BEER: Fast $O(1/T)$ Rate for Decentralized Nonconvex Optimization with Communication Compression","created":"2022-01-31","cited_by_count":41,"area":null},{"id":"2308.10407","title":"Federated Learning for Connected and Automated Vehicles: A Survey of Existing Approaches and Challenges","created":"2023-08-21","cited_by_count":40,"area":null},{"id":"2206.12680","title":"Topology-aware Generalization of Decentralized SGD","created":"2022-06-25","cited_by_count":38,"area":null},{"id":"2302.14428","title":"Stochastic Gradient Descent under Markovian Sampling Schemes","created":"2023-02-28","cited_by_count":38,"area":null},{"id":"2502.14743","title":"Multi-Agent Coordination across Diverse Applications: A Survey","created":"2025-02-20","cited_by_count":37,"area":"agents"},{"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":"2102.07091","title":"Decentralized Riemannian Gradient Descent on the Stiefel Manifold","created":"2021-02-14","cited_by_count":33,"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":"2204.04452","title":"Refined Convergence and Topology Learning for Decentralized SGD with Heterogeneous Data","created":"2022-04-09","cited_by_count":32,"area":null},{"id":"2206.05091","title":"Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging","created":"2022-06-10","cited_by_count":27,"area":null},{"id":"2210.07881","title":"Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate","created":"2022-10-14","cited_by_count":25,"area":null},{"id":"2210.07863","title":"Revisiting Optimal Convergence Rate for Smooth and Non-convex Stochastic Decentralized Optimization","created":"2022-10-14","cited_by_count":23,"area":null},{"id":"2102.06752","title":"A Hybrid Variance-Reduced Method for Decentralized Stochastic Non-Convex Optimization","created":"2021-02-12","cited_by_count":21,"area":null},{"id":"2310.01972","title":"Epidemic Learning: Boosting Decentralized Learning with Randomized Communication","created":"2023-10-03","cited_by_count":21,"area":null},{"id":"2205.13054","title":"Scalable and Low-Latency Federated Learning with Cooperative Mobile Edge Networking","created":"2022-05-25","cited_by_count":18,"area":null},{"id":"2303.10677","title":"A Survey of Federated Learning for Connected and Automated Vehicles","created":"2023-03-19","cited_by_count":17,"area":null},{"id":"2110.01165","title":"DESTRESS: Computation-Optimal and Communication-Efficient Decentralized Nonconvex Finite-Sum Optimization","created":"2021-10-04","cited_by_count":16,"area":null},{"id":"2303.10695","title":"On the Convergence of Decentralized Federated Learning Under Imperfect Information Sharing","created":"2023-03-19","cited_by_count":16,"area":null},{"id":"2105.04851","title":"Improving the Transient Times for Distributed Stochastic Gradient Methods","created":"2021-05-11","cited_by_count":13,"area":null},{"id":"2104.07365","title":"D-Cliques: Compensating for Data Heterogeneity with Topology in Decentralized Federated Learning","created":"2021-04-15","cited_by_count":12,"area":null},{"id":"2204.06477","title":"Data-heterogeneity-aware Mixing for Decentralized Learning","created":"2022-04-13","cited_by_count":12,"area":null},{"id":"2207.03730","title":"Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology","created":"2022-07-08","cited_by_count":10,"area":null},{"id":"2301.05872","title":"CEDAS: A Compressed Decentralized Stochastic Gradient Method with Improved Convergence","created":"2023-01-14","cited_by_count":9,"area":null},{"id":"2305.09896","title":"Convergence and Privacy of Decentralized Nonconvex Optimization with Gradient Clipping and Communication Compression","created":"2023-05-17","cited_by_count":9,"area":null},{"id":"2305.11420","title":"Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence","created":"2023-05-19","cited_by_count":9,"area":null},{"id":"2310.20369","title":"Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm","created":"2023-10-31","cited_by_count":9,"area":null},{"id":"2409.17446","title":"Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability","created":"2024-09-26","cited_by_count":9,"area":null},{"id":"2101.09346","title":"On the Local Linear Rate of Consensus on the Stiefel Manifold","created":"2021-01-22","cited_by_count":8,"area":null},{"id":"2105.01231","title":"GT-STORM: Taming Sample, Communication, and Memory Complexities in Decentralized Non-Convex Learning","created":"2021-05-04","cited_by_count":8,"area":null},{"id":"2107.10706","title":"Distributed Saddle-Point Problems Under Similarity","created":"2021-07-22","cited_by_count":8,"area":null},{"id":"2402.07471","title":"Differentially Private Decentralized Learning with Random Walks","created":"2024-02-12","cited_by_count":8,"area":null},{"id":"2102.05715","title":"Sparse-Push: Communication- & Energy-Efficient Decentralized Distributed Learning over Directed & Time-Varying Graphs with non-IID Datasets","created":"2021-02-10","cited_by_count":7,"area":null},{"id":"2112.15287","title":"Distributed Random Reshuffling over Networks","created":"2021-12-31","cited_by_count":7,"area":null},{"id":"2208.04845","title":"Quantization enabled Privacy Protection in Decentralized Stochastic Optimization","created":"2022-08-07","cited_by_count":7,"area":null},{"id":"2308.10547","title":"Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold","created":"2023-08-21","cited_by_count":7,"area":null},{"id":"2403.15654","title":"The Effectiveness of Local Updates for Decentralized Learning under Data Heterogeneity","created":"2024-03-23","cited_by_count":7,"area":null},{"id":"2411.00284","title":"SimpleFSDP: Simpler Fully Sharded Data Parallel with torch.compile","created":"2024-11-01","cited_by_count":7,"area":null},{"id":"2306.00256","title":"DSGD-CECA: Decentralized SGD with Communication-Optimal Exact Consensus Algorithm","created":"2023-06-01","cited_by_count":6,"area":null},{"id":"2303.02532","title":"PRECISION: Decentralized Constrained Min-Max Learning with Low Communication and Sample Complexities","created":"2023-03-05","cited_by_count":5,"area":null},{"id":"2312.10815","title":"DePRL: Achieving Linear Convergence Speedup in Personalized Decentralized Learning with Shared Representations","created":"2023-12-17","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":"2102.03394","title":"Network Support for High-performance Distributed Machine Learning","created":"2021-02-05","cited_by_count":4,"area":null},{"id":"2112.02129","title":"Distributed Adaptive Learning Under Communication Constraints","created":"2021-12-03","cited_by_count":4,"area":null},{"id":"2201.13288","title":"A Regret Minimization Approach to Multi-Agent Control","created":"2022-01-28","cited_by_count":4,"area":null},{"id":"2204.00489","title":"Accelerating Federated Edge Learning via Topology Optimization","created":"2022-04-01","cited_by_count":4,"area":null},{"id":"2406.00621","title":"Log-Scale Quantization in Distributed First-Order Methods: Gradient-based Learning from Distributed Data","created":"2024-06-02","cited_by_count":4,"area":null},{"id":"2407.20611","title":"The Entrapment Problem in Random Walk Decentralized Learning","created":"2024-07-30","cited_by_count":4,"area":null},{"id":"2408.08628","title":"A survey on secure decentralized optimization and learning","created":"2024-08-16","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":"2511.12836","title":"DIGing--SGLD: Decentralized and Scalable Langevin Sampling over Time--Varying Networks","created":"2025-11-16","cited_by_count":4,"area":null},{"id":"2102.06280","title":"Straggler-Resilient Distributed Machine Learning with Dynamic Backup Workers","created":"2021-02-11","cited_by_count":3,"area":null},{"id":"2106.03585","title":"Asynchronous speedup in decentralized optimization","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2202.05812","title":"Distributed saddle point problems for strongly concave-convex functions","created":"2022-02-11","cited_by_count":3,"area":null},{"id":"2304.04326","title":"Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learning","created":"2023-04-09","cited_by_count":3,"area":"distill"},{"id":"2306.06559","title":"Straggler-Resilient Decentralized Learning via Adaptive Asynchronous Updates","created":"2023-06-11","cited_by_count":3,"area":null},{"id":"2309.09977","title":"A Multi-Token Coordinate Descent Method for Semi-Decentralized Vertical Federated Learning","created":"2023-09-18","cited_by_count":3,"area":null},{"id":"2405.10618","title":"Distributed Event-Based Learning via ADMM","created":"2024-05-17","cited_by_count":3,"area":null},{"id":"2409.17189","title":"Decentralized Federated Learning with Gradient Tracking over Time-Varying Directed Networks","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2501.15259","title":"Scalable Decentralized Learning with Teleportation","created":"2025-01-25","cited_by_count":3,"area":null},{"id":"2105.13348","title":"Optimization in Open Networks via Dual Averaging","created":"2021-05-27","cited_by_count":2,"area":null},{"id":"2208.13643","title":"A Variance-Reduced Stochastic Gradient Tracking Algorithm for Decentralized Optimization with Orthogonality Constraints","created":"2022-08-29","cited_by_count":2,"area":null},{"id":"2211.04088","title":"A Penalty-Based Method for Communication-Efficient Decentralized Bilevel Programming","created":"2022-11-08","cited_by_count":2,"area":null},{"id":"2306.12037","title":"Distributed Random Reshuffling Methods with Improved Convergence","created":"2023-06-21","cited_by_count":2,"area":null},{"id":"2311.18787","title":"Communication-Efficient Federated Optimization over Semi-Decentralized Networks","created":"2023-11-30","cited_by_count":2,"area":null},{"id":"2312.11861","title":"A Proximal Gradient Method With Probabilistic Multi-Gossip Communications for Decentralized Composite Optimization","created":"2023-12-19","cited_by_count":2,"area":null},{"id":"2401.13779","title":"Faster Convergence with Less Communication: Broadcast-Based Subgraph Sampling for Decentralized Learning over Wireless Networks","created":"2024-01-24","cited_by_count":2,"area":null},{"id":"2403.13247","title":"FedNMUT -- Federated Noisy Model Update Tracking Convergence Analysis","created":"2024-03-20","cited_by_count":2,"area":null},{"id":"2404.02511","title":"Stochastic Constrained Decentralized Optimization for Machine Learning with Fewer Data Oracles: a Gradient Sliding Approach","created":"2024-04-03","cited_by_count":2,"area":null},{"id":"2409.04022","title":"Heterogeneity-Aware Cooperative Federated Edge Learning with Adaptive Computation and Communication Compression","created":"2024-09-06","cited_by_count":2,"area":null},{"id":"2508.04950","title":"Compressed Decentralized Momentum Stochastic Gradient Methods for Nonconvex Optimization","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2111.02949","title":"Finite-Time Consensus Learning for Decentralized Optimization with Nonlinear Gossiping","created":"2021-11-04","cited_by_count":1,"area":null},{"id":"2111.06530","title":"Distributed Sparse Regression via Penalization","created":"2021-11-12","cited_by_count":1,"area":null},{"id":"2111.12665","title":"Finite-Time Error Bounds for Distributed Linear Stochastic Approximation","created":"2021-11-24","cited_by_count":1,"area":null},{"id":"2112.10389","title":"Decentralized Stochastic Proximal Gradient Descent with Variance Reduction over Time-varying Networks","created":"2021-12-20","cited_by_count":1,"area":null},{"id":"2205.00473","title":"A Survey on Distributed Online Optimization and Game","created":"2022-05-01","cited_by_count":1,"area":null},{"id":"2206.04113","title":"Push--Pull with Device Sampling","created":"2022-06-08","cited_by_count":1,"area":null},{"id":"2207.09657","title":"Reducing Training Time in Cross-Silo Federated Learning using Multigraph Topology","created":"2022-07-20","cited_by_count":1,"area":null},{"id":"2207.10969","title":"Convergence Theory of Generalized Distributed Subgradient Method with Random Quantization","created":"2022-07-22","cited_by_count":1,"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":"2304.14024","title":"Attacks on Robust Distributed Learning Schemes via Sensitivity Curve Maximization","created":"2023-04-27","cited_by_count":1,"area":null},{"id":"2403.11565","title":"Convergence of Decentralized Stochastic Subgradient-based Methods for Nonsmooth Nonconvex functions","created":"2024-03-18","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":"2405.19513","title":"Decentralized Optimization in Time-Varying Networks with Arbitrary Delays","created":"2024-05-29","cited_by_count":1,"area":null},{"id":"2406.06520","title":"Decentralized Personalized Federated Learning","created":"2024-06-10","cited_by_count":1,"area":null},{"id":"2501.19082","title":"A Bias-Correction Decentralized Stochastic Gradient Algorithm with Momentum Acceleration","created":"2025-01-31","cited_by_count":1,"area":null},{"id":"2503.11828","title":"Performance Analysis of Decentralized Federated Learning Deployments","created":"2025-03-14","cited_by_count":1,"area":null},{"id":"2601.11435","title":"Near-Optimal Decentralized Stochastic Nonconvex Optimization with Heavy-Tailed Noise","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2606.09154","title":"Improved Convergence Analysis of Topology Dependence in Decentralized SGD","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2310.13969","title":"Distributed Linear Regression with Compositional Covariates","created":"2023-10-21","cited_by_count":0,"area":null},{"id":"2311.03496","title":"Asynchronous Local Computations in Distributed Bayesian Learning","created":"2023-11-06","cited_by_count":0,"area":null},{"id":"2402.05148","title":"Cost Optimized Scheduling in Modular Electrolysis Plants","created":"2024-02-07","cited_by_count":0,"area":null},{"id":"2409.04998","title":"A Double Tracking Method for Optimization with Decentralized Generalized Orthogonality Constraints","created":"2024-09-08","cited_by_count":0,"area":null}],"next_cursor":"100"}