{"total":105,"rows":[{"id":"2102.07053","title":"Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients","created":"2021-02-14","cited_by_count":123,"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":"2110.04175","title":"RelaySum for Decentralized Deep Learning on Heterogeneous Data","created":"2021-10-08","cited_by_count":39,"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":"2206.10870","title":"Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks","created":"2022-06-22","cited_by_count":32,"area":null},{"id":"2105.08023","title":"Removing Data Heterogeneity Influence Enhances Network Topology Dependence of Decentralized SGD","created":"2021-05-17","cited_by_count":29,"area":null},{"id":"2106.08315","title":"Decentralized Local Stochastic Extra-Gradient for Variational Inequalities","created":"2021-06-15","cited_by_count":25,"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":"2210.12839","title":"Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity","created":"2022-10-23","cited_by_count":21,"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":"2106.08011","title":"Over-the-Air Decentralized Federated Learning","created":"2021-06-15","cited_by_count":18,"area":null},{"id":"2206.15025","title":"On the Convergence of Distributed Stochastic Bilevel Optimization Algorithms over a Network","created":"2022-06-30","cited_by_count":14,"area":null},{"id":"2305.16297","title":"Unbiased Compression Saves Communication in Distributed Optimization: When and How Much?","created":"2023-05-25","cited_by_count":14,"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":"2106.07243","title":"Compressed Gradient Tracking for Decentralized Optimization Over General Directed Networks","created":"2021-06-14","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":"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":"2305.04792","title":"Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data","created":"2023-05-08","cited_by_count":12,"area":null},{"id":"2205.03884","title":"Decentralized Stochastic Optimization with Inherent Privacy Protection","created":"2022-05-08","cited_by_count":11,"area":null},{"id":"2212.02724","title":"Decentralized Stochastic Gradient Descent Ascent for Finite-Sum Minimax Problems","created":"2022-12-06","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":"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":"2204.03726","title":"Decentralized Event-Triggered Federated Learning with Heterogeneous Communication Thresholds","created":"2022-04-07","cited_by_count":9,"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":"2305.11420","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":"2405.00965","title":"Robust Decentralized Learning with Local Updates and Gradient Tracking","created":"2024-05-02","cited_by_count":8,"area":null},{"id":"2108.04448","title":"Decentralized Composite Optimization with Compression","created":"2021-08-10","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":"2212.02376","title":"DIAMOND: Taming Sample and Communication Complexities in Decentralized Bilevel Optimization","created":"2022-12-05","cited_by_count":7,"area":null},{"id":"2306.02570","title":"When Decentralized Optimization Meets Federated Learning","created":"2023-06-05","cited_by_count":7,"area":null},{"id":"2308.07761","title":"NeFL: Nested Model Scaling for Federated Learning with System Heterogeneous Clients","created":"2023-08-15","cited_by_count":7,"area":null},{"id":"2311.08945","title":"A Single-Loop Algorithm for Decentralized Bilevel Optimization","created":"2023-11-15","cited_by_count":7,"area":null},{"id":"2110.05597","title":"Learning to Coordinate in Multi-Agent Systems: A Coordinated Actor-Critic Algorithm and Finite-Time Guarantees","created":"2021-10-11","cited_by_count":6,"area":null},{"id":"2112.02813","title":"MDPGT: Momentum-based Decentralized Policy Gradient Tracking","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2305.13041","title":"Distributed Learning over Networks with Graph-Attention-Based Personalization","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2107.07211","title":"Decentralized Bayesian Learning with Metropolis-Adjusted Hamiltonian Monte Carlo","created":"2021-07-15","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":"2301.12677","title":"Distributed Stochastic Optimization under a General Variance Condition","created":"2023-01-30","cited_by_count":4,"area":null},{"id":"2302.09766","title":"A One-Sample Decentralized Proximal Algorithm for Non-Convex Stochastic Composite Optimization","created":"2023-02-20","cited_by_count":4,"area":null},{"id":"2304.10902","title":"Near-Optimal Decentralized Momentum Method for Nonconvex-PL Minimax Problems","created":"2023-04-21","cited_by_count":4,"area":null},{"id":"2306.07159","title":"On the Computation-Communication Trade-Off with A Flexible Gradient Tracking Approach","created":"2023-06-12","cited_by_count":4,"area":null},{"id":"2510.01377","title":"DeMuon: A Decentralized Muon for Matrix Optimization over Graphs","created":"2025-10-01","cited_by_count":4,"area":null},{"id":"2202.00509","title":"Decentralized Stochastic Variance Reduced Extragradient Method","created":"2022-02-01","cited_by_count":3,"area":null},{"id":"2404.08079","title":"DIMAT: Decentralized Iterative Merging-And-Training for Deep Learning Models","created":"2024-04-11","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":"2509.02970","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","created":"2025-09-03","cited_by_count":3,"area":null},{"id":"2105.14385","title":"On Centralized and Distributed Mirror Descent: Convergence Analysis Using Quadratic Constraints","created":"2021-05-29","cited_by_count":2,"area":null},{"id":"2202.03346","title":"Variance reduced stochastic optimization over directed graphs with row and column stochastic weights","created":"2022-02-07","cited_by_count":2,"area":null},{"id":"2210.05618","title":"Zero-Order One-Point Estimate with Distributed Stochastic Gradient-Tracking Technique","created":"2022-10-11","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":"2307.11617","title":"Robust Fully-Asynchronous Methods for Distributed Training over General Architecture","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2310.16105","title":"Locally Differentially Private Gradient Tracking for Distributed Online Learning over Directed Graphs","created":"2023-10-24","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":"2403.13247","title":"FedNMUT -- Federated Noisy Model Update Tracking Convergence Analysis","created":"2024-03-20","cited_by_count":2,"area":null},{"id":"2409.20289","title":"Distributed NeRF Learning for Collaborative Multi-Robot Perception","created":"2024-09-30","cited_by_count":2,"area":null},{"id":"2503.23726","title":"PDSL: Privacy-Preserved Decentralized Stochastic Learning with Heterogeneous Data Distribution","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2107.12065","title":"Provably Accelerated Decentralized Gradient Method Over Unbalanced Directed Graphs","created":"2021-07-26","cited_by_count":1,"area":null},{"id":"2110.15092","title":"A Law of Iterated Logarithm for Multi-Agent Reinforcement Learning","created":"2021-10-27","cited_by_count":1,"area":null},{"id":"2111.12961","title":"Distributed Policy Gradient with Variance Reduction in Multi-Agent Reinforcement Learning","created":"2021-11-25","cited_by_count":1,"area":null},{"id":"2306.13892","title":"Generalizing Differentially Private Decentralized Deep Learning with Multi-Agent Consensus","created":"2023-06-24","cited_by_count":1,"area":null},{"id":"2310.00638","title":"A primal-dual perspective for distributed TD-learning","created":"2023-10-01","cited_by_count":1,"area":null},{"id":"2310.07983","title":"Achieving Linear Speedup with ProxSkip in Distributed Stochastic Optimization","created":"2023-10-12","cited_by_count":1,"area":null},{"id":"2403.06535","title":"Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning","created":"2024-03-11","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":"2406.02939","title":"Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive Stepsizes","created":"2024-06-05","cited_by_count":1,"area":null},{"id":"2410.05942","title":"Single Point-Based Distributed Zeroth-Order Optimization with a Non-Convex Stochastic Objective Function","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2410.19319","title":"Fully First-Order Methods for Decentralized Bilevel Optimization","created":"2024-10-25","cited_by_count":1,"area":null},{"id":"2411.00365","title":"ROSS: RObust decentralized Stochastic learning based on Shapley values","created":"2024-11-01","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":"2506.00961","title":"Enhancing Parallelism in Decentralized Stochastic Convex Optimization","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2506.05791","title":"Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2510.06141","title":"High-Probability Convergence Guarantees of Decentralized SGD","created":"2025-10-07","cited_by_count":1,"area":null},{"id":"2601.07021","title":"Tight Analysis of Decentralized SGD: A Markov Chain Perspective","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2606.07496","title":"Accelerated Decentralized Stochastic Gradient Descent for Strongly Convex Optimization","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2211.12640","title":"Resource-Constrained Decentralized Federated Learning via Personalized Event-Triggering","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2307.13430","title":"Achieving Linear Speedup in Decentralized Stochastic Compositional Minimax Optimization","created":"2023-07-25","cited_by_count":0,"area":null},{"id":"2310.06217","title":"Federated Multi-Level Optimization over Decentralized Networks","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2310.14348","title":"DePAint: A Decentralized Safe Multi-Agent Reinforcement Learning Algorithm considering Peak and Average Constraints","created":"2023-10-22","cited_by_count":0,"area":null},{"id":"2311.05760","title":"Compressed and Sparse Models for Non-Convex Decentralized Learning","created":"2023-11-09","cited_by_count":0,"area":null},{"id":"2403.02589","title":"MUSIC: Accelerated Convergence for Distributed Optimization With Inexact and Exact Methods","created":"2024-03-05","cited_by_count":0,"area":null},{"id":"2407.02689","title":"Accelerating Distributed Optimization: A Primal-Dual Perspective on Local Steps","created":"2024-07-02","cited_by_count":0,"area":null},{"id":"2407.02765","title":"Graphon Particle Systems, Part II: Dynamics of Distributed Stochastic Continuum Optimization","created":"2024-07-03","cited_by_count":0,"area":null},{"id":"2503.16123","title":"Distributed Learning over Arbitrary Topology: Linear Speed-Up with Polynomial Transient Time","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2504.12742","title":"Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum","created":"2025-04-17","cited_by_count":0,"area":null},{"id":"2508.20645","title":"A Hybrid Stochastic Gradient Tracking Method for Distributed Online Optimization Over Time-Varying Directed Networks","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2508.20898","title":"CoCoL: A Communication Efficient Decentralized Collaborative Method for Multi-Robot Systems","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2509.18129","title":"Pareto-optimal Trade-offs Between Communication and Computation with Flexible Gradient Tracking","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2509.18134","title":"A Weighted Gradient Tracking Privacy-Preserving Method for Distributed Optimization","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2511.19513","title":"Row-Stochastic Matrices Can Provably Outperform Doubly Stochastic Matrices in Decentralized Learning","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2512.01732","title":"Beyond Scaffold: A Unified Spatio-Temporal Gradient Tracking Method","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2601.01493","title":"Accelerating Decentralized Optimization via Overlapping Local Steps","created":"2026-01-04","cited_by_count":0,"area":null},{"id":"2601.03566","title":"Provably Convergent Decentralized Optimization over Directed Graphs under Generalized Smoothness","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2602.00791","title":"Sporadic Gradient Tracking over Directed Graphs: A Theoretical Perspective on Decentralized Federated Learning","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.02899","title":"Decentralized SGD with Controlled Disagreement Finds Flatter Minima","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.11789","title":"Decentralized Non-convex Stochastic Optimization with Heterogeneous Variance","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.27962","title":"Gradient Manipulation in Distributed Stochastic Gradient Descent with Strategic Agents: Truthful Incentives with Convergence Guarantees","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.18237","title":"Semantic-based Distributed Learning for Diverse and Discriminative Representations","created":"2026-04-20","cited_by_count":0,"area":null}],"next_cursor":"100"}