{"total":138,"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":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134,"area":null},{"id":"2206.01288","title":"Decentralized Training of Foundation Models in Heterogeneous Environments","created":"2022-06-02","cited_by_count":87,"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":"2110.13363","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":"2104.11981","title":"DecentLaM: Decentralized Momentum SGD for Large-batch Deep Training","created":"2021-04-24","cited_by_count":40,"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":"2206.12680","title":"Topology-aware Generalization of Decentralized SGD","created":"2022-06-25","cited_by_count":38,"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":"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":"2301.01313","title":"Decentralized Gradient Tracking with Local Steps","created":"2023-01-03","cited_by_count":32,"area":null},{"id":"2202.01545","title":"Byzantine-Robust Decentralized Learning via ClippedGossip","created":"2022-02-03","cited_by_count":31,"area":null},{"id":"2206.01299","title":"Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees","created":"2022-06-02","cited_by_count":30,"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":"2206.04621","title":"A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learning","created":"2022-06-09","cited_by_count":27,"area":null},{"id":"2103.00543","title":"On the Utility of Gradient Compression in Distributed Training Systems","created":"2021-02-28","cited_by_count":26,"area":null},{"id":"2105.09080","title":"Accelerating Gossip SGD with Periodic Global Averaging","created":"2021-05-19","cited_by_count":25,"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":"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":"2102.12528","title":"Preserved central model for faster bidirectional compression in distributed settings","created":"2021-02-24","cited_by_count":21,"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":"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":"2306.10015","title":"Just One Byte (per gradient): A Note on Low-Bandwidth Decentralized Language Model Finetuning Using Shared Randomness","created":"2023-06-16","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":"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":"2105.07806","title":"Towards Demystifying Serverless Machine Learning Training","created":"2021-05-17","cited_by_count":16,"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":"2111.04287","title":"BlueFog: Make Decentralized Algorithms Practical for Optimization and Deep Learning","created":"2021-11-08","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":"2306.02913","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","created":"2023-06-05","cited_by_count":15,"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":"2104.06685","title":"BROADCAST: Reducing Both Stochastic and Compression Noise to Robustify Communication-Efficient Federated Learning","created":"2021-04-14","cited_by_count":13,"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":"2107.01499","title":"BAGUA: Scaling up Distributed Learning with System Relaxations","created":"2021-07-03","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":"2104.12678","title":"Semi-Decentralized Federated Edge Learning for Fast Convergence on Non-IID Data","created":"2021-04-26","cited_by_count":12,"area":null},{"id":"2105.06697","title":"Innovation Compression for Communication-efficient Distributed Optimization with Linear Convergence","created":"2021-05-14","cited_by_count":12,"area":null},{"id":"2112.10313","title":"Semi-Decentralized Federated Edge Learning with Data and Device Heterogeneity","created":"2021-12-20","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":"2305.04792","title":"Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data","created":"2023-05-08","cited_by_count":12,"area":null},{"id":"2210.13767","title":"Networked Signal and Information Processing","created":"2022-10-25","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":"2301.05872","title":"CEDAS: A Compressed Decentralized Stochastic Gradient Method with Improved Convergence","created":"2023-01-14","cited_by_count":9,"area":null},{"id":"2301.09732","title":"Backdoor Attacks in Peer-to-Peer Federated Learning","created":"2023-01-23","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":"2405.17517","title":"WASH: Train your Ensemble with Communication-Efficient Weight Shuffling, then Average","created":"2024-05-27","cited_by_count":9,"area":null},{"id":"2112.13381","title":"FRuDA: Framework for Distributed Adversarial Domain Adaptation","created":"2021-12-26","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":"2509.26337","title":"FedMuon: Federated Learning with Bias-corrected LMO-based Optimization","created":"2025-09-30","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":"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":"2111.01221","title":"Robust Federated Learning via Over-The-Air Computation","created":"2021-11-01","cited_by_count":6,"area":null},{"id":"2202.00255","title":"DoCoM: Compressed Decentralized Optimization with Near-Optimal Sample Complexity","created":"2022-02-01","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":"2306.00256","title":"DSGD-CECA: Decentralized SGD with Communication-Optimal Exact Consensus Algorithm","created":"2023-06-01","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":"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":"2209.14390","title":"Neighborhood Gradient Clustering: An Efficient Decentralized Learning Method for Non-IID Data Distributions","created":"2022-09-28","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":"2109.07704","title":"Federated Submodel Optimization for Hot and Cold Data Features","created":"2021-09-16","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":"2205.02949","title":"Over-The-Air Federated Learning under Byzantine Attacks","created":"2022-05-05","cited_by_count":4,"area":null},{"id":"2206.00054","title":"Asynchronous Hierarchical Federated Learning","created":"2022-05-31","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":"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":"2312.05248","title":"Topology-Based Reconstruction Prevention for Decentralised Learning","created":"2023-12-08","cited_by_count":4,"area":null},{"id":"2406.01484","title":"Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization","created":"2024-06-03","cited_by_count":4,"area":null},{"id":"2503.07505","title":"From Centralized to Decentralized Federated Learning: Theoretical Insights, Privacy Preservation, and Robustness Challenges","created":"2025-03-10","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":"2202.05812","title":"Distributed saddle point problems for strongly concave-convex functions","created":"2022-02-11","cited_by_count":3,"area":null},{"id":"2301.02151","title":"Beyond spectral gap (extended): The role of the topology in decentralized learning","created":"2023-01-05","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":"2312.04740","title":"Train 'n Trade: Foundations of Parameter Markets","created":"2023-12-07","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":"2501.15259","title":"Scalable Decentralized Learning with Teleportation","created":"2025-01-25","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":"2111.09389","title":"Low Precision Decentralized Distributed Training over IID and non-IID Data","created":"2021-11-17","cited_by_count":2,"area":null},{"id":"2205.03779","title":"Communication Compression for Decentralized Learning with Operator Splitting Methods","created":"2022-05-08","cited_by_count":2,"area":null},{"id":"2206.05830","title":"Stochastic Gradient Descent without Full Data Shuffle","created":"2022-06-12","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":"2307.07113","title":"Variance-reduced accelerated methods for decentralized stochastic double-regularized nonconvex strongly-concave minimax problems","created":"2023-07-14","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":"2308.05292","title":"Byzantine-Robust Decentralized Stochastic Optimization with Stochastic Gradient Noise-Independent Learning Error","created":"2023-08-10","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":"2408.04705","title":"Overlay-based Decentralized Federated Learning in Bandwidth-limited Networks","created":"2024-08-08","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":"2508.04950","title":"Compressed Decentralized Momentum Stochastic Gradient Methods for Nonconvex Optimization","created":"2025-08-07","cited_by_count":2,"area":null}],"next_cursor":"100"}