{"total":219,"rows":[{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"area":null},{"id":"2106.15590","title":"The Values Encoded in Machine Learning Research","created":"2021-06-29","cited_by_count":172,"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":"2308.08165","title":"Stochastic Controlled Averaging for Federated Learning with Communication Compression","created":"2023-08-16","cited_by_count":101,"area":null},{"id":"2111.12444","title":"Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications","created":"2021-11-24","cited_by_count":97,"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":"2306.01603","title":"Decentralized Federated Learning: A Survey and Perspective","created":"2023-06-02","cited_by_count":86,"area":null},{"id":"2206.00187","title":"DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training","created":"2022-06-01","cited_by_count":74,"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":"2107.12048","title":"Decentralized Federated Learning: Balancing Communication and Computing Costs","created":"2021-07-26","cited_by_count":55,"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":"2102.04828","title":"Consensus Control for Decentralized Deep Learning","created":"2021-02-09","cited_by_count":49,"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":"2302.14428","title":"Stochastic Gradient Descent under Markovian Sampling Schemes","created":"2023-02-28","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":"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":"2103.11109","title":"DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation","created":"2021-03-20","cited_by_count":31,"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":"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":"2101.01901","title":"IPLS : A Framework for Decentralized Federated Learning","created":"2021-01-06","cited_by_count":26,"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":"2107.08517","title":"Decentralized federated learning of deep neural networks on non-iid data","created":"2021-07-18","cited_by_count":25,"area":null},{"id":"2205.08443","title":"On the (In)security of Peer-to-Peer Decentralized Machine Learning","created":"2022-05-17","cited_by_count":23,"area":null},{"id":"2102.07245","title":"Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization","created":"2021-02-14","cited_by_count":21,"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":"2310.01972","title":"Epidemic Learning: Boosting Decentralized Learning with Randomized Communication","created":"2023-10-03","cited_by_count":21,"area":null},{"id":"2205.05040","title":"A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks","created":"2022-05-10","cited_by_count":20,"area":null},{"id":"2205.05632","title":"On Distributed Adaptive Optimization with Gradient Compression","created":"2022-05-11","cited_by_count":19,"area":null},{"id":"2107.00961","title":"ResIST: Layer-Wise Decomposition of ResNets for Distributed Training","created":"2021-07-02","cited_by_count":18,"area":null},{"id":"2304.08322","title":"Decentralized Learning Made Easy with DecentralizePy","created":"2023-04-17","cited_by_count":18,"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":"2206.10189","title":"A General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updates","created":"2022-06-21","cited_by_count":17,"area":null},{"id":"2402.16828","title":"Training Neural Networks from Scratch with Parallel Low-Rank Adapters","created":"2024-02-26","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":"2111.04287","title":"BlueFog: Make Decentralized Algorithms Practical for Optimization and Deep Learning","created":"2021-11-08","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":"2310.20452","title":"AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms","created":"2023-10-31","cited_by_count":16,"area":null},{"id":"2107.11304","title":"Finite-Bit Quantization For Distributed Algorithms With Linear Convergence","created":"2021-07-23","cited_by_count":15,"area":null},{"id":"2311.05645","title":"EControl: Fast Distributed Optimization with Compression and Error Control","created":"2023-11-06","cited_by_count":15,"area":null},{"id":"2112.05120","title":"On Convergence of Federated Averaging Langevin Dynamics","created":"2021-12-09","cited_by_count":14,"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":"2103.11102","title":"Projection-free Distributed Online Learning with Sublinear Communication Complexity","created":"2021-03-20","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":"2302.02390","title":"Quantized Distributed Training of Large Models with Convergence Guarantees","created":"2023-02-05","cited_by_count":13,"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":"2106.07243","title":"Compressed Gradient Tracking for Decentralized Optimization Over General Directed Networks","created":"2021-06-14","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":"2307.07652","title":"DIGEST: Fast and Communication Efficient Decentralized Learning with Local Updates","created":"2023-07-14","cited_by_count":12,"area":null},{"id":"2310.09804","title":"Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates","created":"2023-10-15","cited_by_count":12,"area":null},{"id":"2506.01260","title":"Subspace Networks: Scaling Decentralized Training with Communication-Efficient Model Parallelism","created":"2025-06-02","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":"2205.14473","title":"Efficient-Adam: Communication-Efficient Distributed Adam","created":"2022-05-28","cited_by_count":11,"area":null},{"id":"2206.03588","title":"Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation","created":"2022-06-07","cited_by_count":11,"area":null},{"id":"2311.00465","title":"Asynchronous SGD on Graphs: a Unified Framework for Asynchronous Decentralized and Federated Optimization","created":"2023-11-01","cited_by_count":11,"area":null},{"id":"2102.12357","title":"Wirelessly Powered Federated Edge Learning: Optimal Tradeoffs Between Convergence and Power Transfer","created":"2021-02-24","cited_by_count":10,"area":null},{"id":"2205.15614","title":"Communication-Efficient Distributionally Robust Decentralized Learning","created":"2022-05-31","cited_by_count":10,"area":null},{"id":"2212.07534","title":"Decentralized Nonconvex Optimization with Guaranteed Privacy and Accuracy","created":"2022-12-14","cited_by_count":10,"area":null},{"id":"2308.00263","title":"Asynchronous Federated Learning with Bidirectional Quantized Communications and Buffered Aggregation","created":"2023-08-01","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":"2404.09536","title":"Noiseless Privacy-Preserving Decentralized Learning","created":"2024-04-15","cited_by_count":9,"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":"2105.09400","title":"Separation of Powers in Federated Learning","created":"2021-05-19","cited_by_count":8,"area":null},{"id":"2305.15157","title":"Towards More Suitable Personalization in Federated Learning via Decentralized Partial Model Training","created":"2023-05-24","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":"2108.04448","title":"Decentralized Composite Optimization with Compression","created":"2021-08-10","cited_by_count":7,"area":null},{"id":"2205.14905","title":"Confederated Learning: Federated Learning with Decentralized Edge Servers","created":"2022-05-30","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":"2209.07821","title":"Quantization for decentralized learning under subspace constraints","created":"2022-09-16","cited_by_count":7,"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":"2202.11655","title":"TEE-based decentralized recommender systems: The raw data sharing redemption","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2209.05148","title":"Personalized Federated Learning with Communication Compression","created":"2022-09-12","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":"2301.09848","title":"Gossiped and Quantized Online Multi-Kernel Learning","created":"2023-01-24","cited_by_count":6,"area":null},{"id":"2303.08423","title":"Communication-Efficient Design for Quantized Decentralized Federated Learning","created":"2023-03-15","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":"2306.04377","title":"Get More for Less in Decentralized Learning Systems","created":"2023-06-07","cited_by_count":6,"area":null},{"id":"2410.12918","title":"Boosting Asynchronous Decentralized Learning with Model Fragmentation","created":"2024-10-16","cited_by_count":6,"area":null},{"id":"2102.07521","title":"Distributed Online Learning for Joint Regret with Communication Constraints","created":"2021-02-15","cited_by_count":5,"area":null},{"id":"2302.11197","title":"Quantized Low-Rank Multivariate Regression with Random Dithering","created":"2023-02-22","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":"2406.13533","title":"DRACO: Decentralized Asynchronous Federated Learning over Row-Stochastic Wireless Networks","created":"2024-06-19","cited_by_count":5,"area":null},{"id":"2102.07767","title":"Communication-efficient Distributed Cooperative Learning with Compressed Beliefs","created":"2021-02-14","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":"2203.02383","title":"Distributed Methods with Absolute Compression and Error Compensation","created":"2022-03-04","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":"2306.06603","title":"Task-Oriented Integrated Sensing, Computation and Communication for Wireless Edge AI","created":"2023-06-11","cited_by_count":4,"area":null}],"next_cursor":"100"}