{"total":78,"rows":[{"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":"2110.13363","title":"Exponential Graph is Provably Efficient for Decentralized Deep Training","created":"2021-10-26","cited_by_count":56,"area":null},{"id":"2205.13692","title":"FedAvg with Fine Tuning: Local Updates Lead to Representation Learning","created":"2022-05-27","cited_by_count":56,"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":"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":"2105.00321","title":"Regret and Cumulative Constraint Violation Analysis for Distributed Online Constrained Convex Optimization","created":"2021-05-01","cited_by_count":21,"area":null},{"id":"2210.14026","title":"SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication","created":"2022-10-25","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":"2111.04287","title":"BlueFog: Make Decentralized Algorithms Practical for Optimization and Deep Learning","created":"2021-11-08","cited_by_count":16,"area":null},{"id":"2202.01268","title":"DASHA: Distributed Nonconvex Optimization with Communication Compression, Optimal Oracle Complexity, and No Client Synchronization","created":"2022-02-02","cited_by_count":16,"area":null},{"id":"2306.02913","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","created":"2023-06-05","cited_by_count":15,"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":"2104.02596","title":"Accelerated Gradient Tracking over Time-varying Graphs for Decentralized Optimization","created":"2021-04-06","cited_by_count":11,"area":null},{"id":"2210.13767","title":"Networked Signal and Information Processing","created":"2022-10-25","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":"2405.17876","title":"Decentralized Directed Collaboration for Personalized Federated Learning","created":"2024-05-28","cited_by_count":9,"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":"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":"2109.01806","title":"On Faster Convergence of Scaled Sign Gradient Descent","created":"2021-09-04","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":"2503.20117","title":"Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2209.01750","title":"Boost Decentralized Federated Learning in Vehicular Networks by Diversifying Data Sources","created":"2022-09-05","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":"2406.13533","title":"DRACO: Decentralized Asynchronous Federated Learning over Row-Stochastic Wireless Networks","created":"2024-06-19","cited_by_count":5,"area":null},{"id":"2410.18862","title":"FedSPD: A Soft-clustering Approach for Personalized Decentralized Federated Learning","created":"2024-10-24","cited_by_count":5,"area":null},{"id":"2307.07406","title":"Improved Convergence Analysis and SNR Control Strategies for Federated Learning in the Presence of Noise","created":"2023-07-14","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":"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":"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":"2411.16477","title":"Distributed Online Optimization with Stochastic Agent Availability","created":"2024-11-25","cited_by_count":3,"area":null},{"id":"2109.12340","title":"Distributed Online Optimization with Byzantine Adversarial Agents","created":"2021-09-25","cited_by_count":2,"area":null},{"id":"2209.10105","title":"Distributed Online Non-convex Optimization with Composite Regret","created":"2022-09-21","cited_by_count":2,"area":null},{"id":"2305.04630","title":"Federated Learning in Wireless Networks via Over-the-Air Computations","created":"2023-05-08","cited_by_count":2,"area":null},{"id":"2308.16671","title":"Sparse Decentralized Federated Learning","created":"2023-08-31","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":"2107.12065","title":"Provably Accelerated Decentralized Gradient Method Over Unbalanced Directed Graphs","created":"2021-07-26","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":"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":"2210.02129","title":"Decentralized Hyper-Gradient Computation over Time-Varying Directed Networks","created":"2022-10-05","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":"2312.01227","title":"Distributed Bayesian Estimation in Sensor Networks: Consensus on Marginal Densities","created":"2023-12-02","cited_by_count":1,"area":null},{"id":"2403.06298","title":"Analysis of Total Variation Minimization for Clustered Federated Learning","created":"2024-03-10","cited_by_count":1,"area":null},{"id":"2405.18031","title":"Lower Bounds and Optimal Algorithms for Non-Smooth Convex Decentralized Optimization over Time-Varying Networks","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2412.12837","title":"Exposing the Vulnerability of Decentralized Learning to Membership Inference Attacks Through the Lens of Graph Mixing","created":"2024-12-17","cited_by_count":1,"area":"safety"},{"id":"2508.08606","title":"Distributed optimization: designed for federated learning","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2512.13583","title":"DP-CSGP: Differentially Private Stochastic Gradient Push with Compressed Communication","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2512.24069","title":"Time-varying Mixing Matrix Design for Energy-efficient Decentralized Federated Learning","created":"2025-12-30","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":"2108.03508","title":"The Effect of Training Parameters and Mechanisms on Decentralized Federated Learning based on MNIST Dataset","created":"2021-08-07","cited_by_count":0,"area":null},{"id":"2201.11343","title":"Distributed gradient-based optimization in the presence of dependent aperiodic communication","created":"2022-01-27","cited_by_count":0,"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":"2212.09472","title":"Distributed Unconstrained Optimization with Time-varying Cost Functions","created":"2022-12-12","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":"2404.15273","title":"Estimation Network Design framework for efficient distributed optimization","created":"2024-04-23","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":"2409.19279","title":"Distributed Optimization via Energy Conservation Laws in Dilated Coordinates","created":"2024-09-28","cited_by_count":0,"area":null},{"id":"2411.09267","title":"Towards efficient compression and communication for prototype-based decentralized learning","created":"2024-11-14","cited_by_count":0,"area":null},{"id":"2505.11307","title":"Diffusion Learning with Partial Agent Participation and Local Updates","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2506.05215","title":"Theory of Decentralized Robust Kernel-Based Learning","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2506.15387","title":"Multi-Timescale Primal Dual Hybrid Gradient with Application to Distributed Optimization","created":"2025-06-18","cited_by_count":0,"area":null},{"id":"2507.22311","title":"An Asynchronous Decentralised Optimisation Algorithm for Nonconvex Problems","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2510.25176","title":"Machine Learning and CPU (Central Processing Unit) Scheduling Co-Optimization over a Network of Computing Centers","created":"2025-10-29","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":"2512.24694","title":"Mobility-Assisted Decentralized Federated Learning: Convergence Analysis and A Data-Driven Approach","created":"2025-12-31","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":"2601.05613","title":"PiXTime: A Model for Federated Time Series Forecasting with Heterogeneous Data across Nodes","created":"2026-01-09","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":"2602.20567","title":"Stability and Generalization of Push-Sum Based Decentralized Optimization over Directed Graphs","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2603.02639","title":"Convex and Non-convex Federated Learning with Stale Stochastic Gradients: Diminishing Step Size is All You Need","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.12838","title":"A New Kernel Regularity Condition for Distributed Mirror Descent: Broader Coverage and Simpler Analysis","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2605.26162","title":"On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2606.06687","title":"Towards Serverless Semi-Decentralized Federated Learning with Heterogeneous Optimizers","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2608.01220","title":"Using Non-Lipschitz Signum-based Functions for Distributed Optimization and Machine Learning: Trade-off Between Con-vergence Rate and Optimality Gap","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.25535","title":"Resilient Decentralized Wireless Federated Learning via Gradient Tracking with AdamW","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.17601","title":"Decentralized Optimal Equilibrium Learning Over Dynamic Networks","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":null}