{"total":111,"rows":[{"id":"2106.05203","title":"EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback","created":"2021-06-09","cited_by_count":133,"area":null},{"id":"2306.01603","title":"Decentralized Federated Learning: A Survey and Perspective","created":"2023-06-02","cited_by_count":86,"area":null},{"id":"2102.07845","title":"MARINA: Faster Non-Convex Distributed Learning with Compression","created":"2021-02-15","cited_by_count":78,"area":null},{"id":"2102.02888","title":"1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed","created":"2021-02-04","cited_by_count":75,"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":"2106.10207","title":"Distributed Deep Learning in Open Collaborations","created":"2021-06-18","cited_by_count":58,"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":"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":"2107.10996","title":"Communication Efficiency in Federated Learning: Achievements and Challenges","created":"2021-07-23","cited_by_count":40,"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":"2103.02051","title":"Cross-Gradient Aggregation for Decentralized Learning from Non-IID data","created":"2021-03-02","cited_by_count":33,"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":"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":"2305.15155","title":"Momentum Provably Improves Error Feedback!","created":"2023-05-24","cited_by_count":31,"area":null},{"id":"2202.00998","title":"3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation","created":"2022-02-02","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":"2104.06069","title":"1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed","created":"2021-04-13","cited_by_count":24,"area":null},{"id":"2111.05326","title":"The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning","created":"2021-11-09","cited_by_count":23,"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":"2304.08322","title":"Decentralized Learning Made Easy with DecentralizePy","created":"2023-04-17","cited_by_count":18,"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":"2111.04287","title":"BlueFog: Make Decentralized Algorithms Practical for Optimization and Deep Learning","created":"2021-11-08","cited_by_count":16,"area":null},{"id":"2202.06009","title":"Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam","created":"2022-02-12","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":"2106.02797","title":"Neural Distributed Source Coding","created":"2021-06-05","cited_by_count":13,"area":null},{"id":"2202.00955","title":"Asynchronous Decentralized Learning over Unreliable Wireless Networks","created":"2022-02-02","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":"2106.11257","title":"Secure Distributed Training at Scale","created":"2021-06-21","cited_by_count":12,"area":null},{"id":"2111.00705","title":"Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization","created":"2021-11-01","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":"2210.01161","title":"Unbounded Gradients in Federated Learning with Buffered Asynchronous Aggregation","created":"2022-10-03","cited_by_count":12,"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":"2212.02724","title":"Decentralized Stochastic Gradient Descent Ascent for Finite-Sum Minimax Problems","created":"2022-12-06","cited_by_count":11,"area":null},{"id":"2205.15614","title":"Communication-Efficient Distributionally Robust Decentralized Learning","created":"2022-05-31","cited_by_count":10,"area":null},{"id":"2102.08374","title":"IntSGD: Adaptive Floatless Compression of Stochastic Gradients","created":"2021-02-16","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":"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":"2310.20369","title":"Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm","created":"2023-10-31","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":"2110.03294","title":"EF21 with Bells & Whistles: Six Algorithmic Extensions of Modern Error Feedback","created":"2021-10-07","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":"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":"2106.07155","title":"CFedAvg: Achieving Efficient Communication and Fast Convergence in Non-IID Federated Learning","created":"2021-06-14","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":"2306.08289","title":"$\\textbf{A}^2\\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning","created":"2023-06-14","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":"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":"2306.04377","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":"2104.08100","title":"Efficient Ring-topology Decentralized Federated Learning with Deep Generative Models for Industrial Artificial Intelligent","created":"2021-04-15","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":"2210.01176","title":"PersA-FL: Personalized Asynchronous Federated Learning","created":"2022-10-03","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":"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":"2310.19059","title":"Escaping Saddle Points in Heterogeneous Federated Learning via Distributed SGD with Communication Compression","created":"2023-10-29","cited_by_count":4,"area":null},{"id":"2503.08427","title":"Accelerated Distributed Optimization with Compression and Error Feedback","created":"2025-03-11","cited_by_count":4,"area":null},{"id":"2304.04326","title":"Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learning","created":"2023-04-09","cited_by_count":3,"area":"distill"},{"id":"2311.18578","title":"Communication-Efficient Heterogeneous Federated Learning with Generalized Heavy-Ball Momentum","created":"2023-11-30","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":"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":"2210.07703","title":"Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence","created":"2022-10-14","cited_by_count":2,"area":null},{"id":"2303.15378","title":"CoDeC: Communication-Efficient Decentralized Continual Learning","created":"2023-03-27","cited_by_count":2,"area":null},{"id":"2304.03638","title":"Compressed Regression over Adaptive Networks","created":"2023-04-07","cited_by_count":2,"area":null},{"id":"2306.03322","title":"Decentralized Multi-Level Compositional Optimization Algorithms with Level-Independent Convergence Rate","created":"2023-06-06","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":"2310.16106","title":"Decentralized Learning over Wireless Networks with Broadcast-Based Subgraph Sampling","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":"2408.04705","title":"Overlay-based Decentralized Federated Learning in Bandwidth-limited Networks","created":"2024-08-08","cited_by_count":2,"area":null},{"id":"2511.14501","title":"Improved Convergence in Parameter-Agnostic Error Feedback through Momentum","created":"2025-11-18","cited_by_count":2,"area":null},{"id":"2102.09631","title":"Peering Beyond the Gradient Veil with Distributed Auto Differentiation","created":"2021-02-18","cited_by_count":1,"area":null},{"id":"2204.08160","title":"On Arbitrary Compression for Decentralized Consensus and Stochastic Optimization over Directed Networks","created":"2022-04-18","cited_by_count":1,"area":null},{"id":"2305.15264","title":"Error Feedback Shines when Features are Rare","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2401.03083","title":"Energy-efficient Decentralized Learning via Graph Sparsification","created":"2024-01-05","cited_by_count":1,"area":null},{"id":"2403.03292","title":"Averaging Rate Scheduler for Decentralized Learning on Heterogeneous Data","created":"2024-03-05","cited_by_count":1,"area":null},{"id":"2404.05919","title":"AdaGossip: Adaptive Consensus Step-size for Decentralized Deep Learning with Communication Compression","created":"2024-04-09","cited_by_count":1,"area":null},{"id":"2404.19749","title":"Scale-Robust Timely Asynchronous Decentralized Learning","created":"2024-04-30","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":"2508.02993","title":"On the Fast Adaptation of Delayed Clients in Decentralized Federated Learning: A Centroid-Aligned Distillation Approach","created":"2025-08-05","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":"2602.04352","title":"Mosaic Learning: A Framework for Decentralized Learning with Model Fragmentation","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2603.01730","title":"Decentralized Federated Learning by Partial Message Exchange","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.23472","title":"Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2606.09154","title":"Improved Convergence Analysis of Topology Dependence in Decentralized SGD","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2110.04523","title":"An Empirical Study on Compressed Decentralized Stochastic Gradient Algorithms with Overparameterized Models","created":"2021-10-09","cited_by_count":0,"area":null},{"id":"2306.08670","title":"Simple Opinion Dynamics for No-Regret Learning","created":"2023-06-14","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":"2311.05760","title":"Compressed and Sparse Models for Non-Convex Decentralized Learning","created":"2023-11-09","cited_by_count":0,"area":null},{"id":"2405.13961","title":"SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2410.18774","title":"A Stochastic Approximation Approach for Efficient Decentralized Optimization on Random Networks","created":"2024-10-24","cited_by_count":0,"area":null}],"next_cursor":"100"}