{"total":155,"rows":[{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"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":"2104.11375","title":"Decentralized Federated Averaging","created":"2021-04-23","cited_by_count":114,"area":null},{"id":"2204.03809","title":"Federated Learning with Partial Model Personalization","created":"2022-04-08","cited_by_count":114,"area":null},{"id":"2107.12048","title":"Decentralized Federated Learning: Balancing Communication and Computing Costs","created":"2021-07-26","cited_by_count":55,"area":null},{"id":"2102.04828","title":"Consensus Control for Decentralized Deep Learning","created":"2021-02-09","cited_by_count":49,"area":null},{"id":"2104.11981","title":"DecentLaM: Decentralized Momentum SGD for Large-batch Deep Training","created":"2021-04-24","cited_by_count":40,"area":null},{"id":"2206.04723","title":"On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data","created":"2022-06-09","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":"2102.07091","title":"Decentralized Riemannian Gradient Descent on the Stiefel Manifold","created":"2021-02-14","cited_by_count":33,"area":null},{"id":"2111.13293","title":"KNAS: Green Neural Architecture Search","created":"2021-11-26","cited_by_count":33,"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":"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":"2206.03093","title":"Beyond spectral gap: The role of the topology in decentralized learning","created":"2022-06-07","cited_by_count":27,"area":null},{"id":"2105.09080","title":"Accelerating Gossip SGD with Periodic Global Averaging","created":"2021-05-19","cited_by_count":25,"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":"2210.04757","title":"On the Performance of Gradient Tracking with Local Updates","created":"2022-10-10","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":"2102.03990","title":"DeEPCA: Decentralized Exact PCA with Linear Convergence Rate","created":"2021-02-08","cited_by_count":18,"area":null},{"id":"2104.05245","title":"Distributed Learning Systems with First-order Methods","created":"2021-04-12","cited_by_count":17,"area":null},{"id":"2109.03194","title":"On the Convergence of Decentralized Adaptive Gradient Methods","created":"2021-09-07","cited_by_count":17,"area":null},{"id":"2105.07806","title":"Towards Demystifying Serverless Machine Learning Training","created":"2021-05-17","cited_by_count":16,"area":null},{"id":"2205.10998","title":"Semi-Decentralized Federated Learning with Collaborative Relaying","created":"2022-05-23","cited_by_count":16,"area":null},{"id":"2104.03490","title":"Joint Optimization of Communications and Federated Learning Over the Air","created":"2021-04-08","cited_by_count":14,"area":null},{"id":"2501.15361","title":"Decentralized Low-Rank Fine-Tuning of Large Language Models","created":"2025-01-26","cited_by_count":14,"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":"2307.07652","title":"DIGEST: Fast and Communication Efficient Decentralized Learning with Local Updates","created":"2023-07-14","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":"2112.14949","title":"Decentralized Optimization Over the Stiefel Manifold by an Approximate Augmented Lagrangian Function","created":"2021-12-30","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":"2503.14353","title":"Unified Analysis of Decentralized Gradient Descent: a Contraction Mapping Framework","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2104.00399","title":"Distributed support-vector-machine over dynamic balanced directed networks","created":"2021-04-01","cited_by_count":9,"area":null},{"id":"2106.06075","title":"A Decentralized Adaptive Momentum Method for Solving a Class of Min-Max Optimization Problems","created":"2021-06-10","cited_by_count":9,"area":null},{"id":"2211.10777","title":"Non-Coherent Over-the-Air Decentralized Gradient Descent","created":"2022-11-19","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":"2101.01300","title":"A Linearly Convergent Algorithm for Distributed Principal Component Analysis","created":"2021-01-05","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":"2209.07116","title":"On Generalization of Decentralized Learning with Separable Data","created":"2022-09-15","cited_by_count":8,"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":"2306.11201","title":"Adaptive Federated Learning with Auto-Tuned Clients","created":"2023-06-19","cited_by_count":7,"area":null},{"id":"2306.11922","title":"No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths","created":"2023-06-20","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":"2205.06689","title":"Heavy-Tail Phenomenon in Decentralized SGD","created":"2022-05-13","cited_by_count":6,"area":null},{"id":"2208.08681","title":"Communication-Efficient Decentralized Online Continuous DR-Submodular Maximization","created":"2022-08-18","cited_by_count":6,"area":null},{"id":"2212.02387","title":"An Efficient Stochastic Algorithm for Decentralized Nonconvex-Strongly-Concave Minimax Optimization","created":"2022-12-05","cited_by_count":6,"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":"2312.04504","title":"Coordination-free Decentralised Federated Learning on Complex Networks: Overcoming Heterogeneity","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2407.09324","title":"Provable Privacy Advantages of Decentralized Federated Learning via Distributed Optimization","created":"2024-07-12","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":"2202.11850","title":"Robust Federated Learning with Connectivity Failures: A Semi-Decentralized Framework with Collaborative Relaying","created":"2022-02-24","cited_by_count":5,"area":null},{"id":"2205.08364","title":"Network Gradient Descent Algorithm for Decentralized Federated Learning","created":"2022-05-06","cited_by_count":5,"area":null},{"id":"2208.13810","title":"DR-DSGD: A Distributionally Robust Decentralized Learning Algorithm over Graphs","created":"2022-08-29","cited_by_count":5,"area":null},{"id":"2209.01850","title":"DISA: A Dual Inexact Splitting Algorithm for Distributed Convex Composite Optimization","created":"2022-09-05","cited_by_count":5,"area":null},{"id":"2302.03238","title":"Decentralized Inexact Proximal Gradient Method With Network-Independent Stepsizes for Convex Composite Optimization","created":"2023-02-07","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":"2112.05559","title":"Collaborative Learning over Wireless Networks: An Introductory Overview","created":"2021-12-07","cited_by_count":4,"area":null},{"id":"2202.05498","title":"Fast and Robust Sparsity Learning over Networks: A Decentralized Surrogate Median Regression Approach","created":"2022-02-11","cited_by_count":4,"area":null},{"id":"2211.00533","title":"Optimal Complexity in Non-Convex Decentralized Learning over Time-Varying Networks","created":"2022-11-01","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":"2509.07779","title":"Decentralized Online Riemannian Optimization Beyond Hadamard Manifolds","created":"2025-09-09","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":"2112.12373","title":"Decentralized Multi-Task Stochastic Optimization With Compressed Communications","created":"2021-12-23","cited_by_count":3,"area":null},{"id":"2303.13326","title":"Decentralized Adversarial Training over Graphs","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2305.07368","title":"Decentralized Learning over Wireless Networks: The Effect of Broadcast with Random Access","created":"2023-05-12","cited_by_count":3,"area":null},{"id":"2308.03035","title":"Serverless Federated AUPRC Optimization for Multi-Party Collaborative Imbalanced Data Mining","created":"2023-08-06","cited_by_count":3,"area":null},{"id":"2412.01630","title":"Review of Mathematical Optimization in Federated Learning","created":"2024-12-02","cited_by_count":3,"area":null},{"id":"2510.19934","title":"Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via $f$-Differential Privacy","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2204.12663","title":"Understanding A Class of Decentralized and Federated Optimization Algorithms: A Multi-Rate Feedback Control Perspective","created":"2022-04-27","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":"2211.00889","title":"Accelerating Parallel Stochastic Gradient Descent via Non-blocking Mini-batches","created":"2022-11-02","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":"2305.04630","title":"Federated Learning in Wireless Networks via Over-the-Air Computations","created":"2023-05-08","cited_by_count":2,"area":null},{"id":"2309.00520","title":"Robust Online Learning over Networks","created":"2023-09-01","cited_by_count":2,"area":null},{"id":"2312.07338","title":"Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification","created":"2023-12-12","cited_by_count":2,"area":null},{"id":"2403.10423","title":"Quantization Avoids Saddle Points in Distributed Optimization","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2507.06931","title":"DICE: Data Influence Cascade in Decentralized Learning","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2605.00723","title":"Decentralized Proximal Stochastic Gradient Langevin Dynamics","created":"2026-05-01","cited_by_count":2,"area":null},{"id":"2103.07454","title":"EventGraD: Event-Triggered Communication in Parallel Machine Learning","created":"2021-03-12","cited_by_count":1,"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":"2111.06530","title":"Distributed Sparse Regression via Penalization","created":"2021-11-12","cited_by_count":1,"area":null},{"id":"2202.03263","title":"Asynchronous Parallel Incremental Block-Coordinate Descent for Decentralized Machine Learning","created":"2022-02-07","cited_by_count":1,"area":null},{"id":"2210.16790","title":"One Gradient Frank-Wolfe for Decentralized Online Convex and Submodular Optimization","created":"2022-10-30","cited_by_count":1,"area":null},{"id":"2301.12065","title":"Decentralized Entropic Optimal Transport for Distributed Distribution Comparison","created":"2023-01-28","cited_by_count":1,"area":null},{"id":"2302.07323","title":"Federated Learning via Indirect Server-Client Communications","created":"2023-02-14","cited_by_count":1,"area":null},{"id":"2303.09611","title":"Decentralized Riemannian natural gradient methods with Kronecker-product approximations","created":"2023-03-16","cited_by_count":1,"area":null},{"id":"2303.17779","title":"Decentralized Weakly Convex Optimization Over the Stiefel Manifold","created":"2023-03-31","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":"2305.07898","title":"Network-GIANT: Fully distributed Newton-type optimization via harmonic Hessian consensus","created":"2023-05-13","cited_by_count":1,"area":null},{"id":"2306.06375","title":"Optimized Gradient Tracking for Decentralized Online Learning","created":"2023-06-10","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":"2311.16021","title":"Scheduling and Communication Schemes for Decentralized Federated Learning","created":"2023-11-27","cited_by_count":1,"area":null},{"id":"2312.06508","title":"Asynchronous Distributed Optimization with Delay-free Parameters","created":"2023-12-11","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}],"next_cursor":"100"}