{"total":22,"rows":[{"id":"2110.13363","title":"Exponential Graph is Provably Efficient for Decentralized Deep Training","created":"2021-10-26","cited_by_count":56,"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":"2105.09080","title":"Accelerating Gossip SGD with Periodic Global Averaging","created":"2021-05-19","cited_by_count":25,"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":"2503.14353","title":"Unified Analysis of Decentralized Gradient Descent: a Contraction Mapping Framework","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2306.14348","title":"Collaborative and Distributed Bayesian Optimization via Consensus: Showcasing the Power of Collaboration for Optimal Design","created":"2023-06-25","cited_by_count":9,"area":null},{"id":"2101.09346","title":"On the Local Linear Rate of Consensus on the Stiefel Manifold","created":"2021-01-22","cited_by_count":8,"area":null},{"id":"2201.01954","title":"Federated Optimization of Smooth Loss Functions","created":"2022-01-06","cited_by_count":6,"area":null},{"id":"2107.07211","title":"Decentralized Bayesian Learning with Metropolis-Adjusted Hamiltonian Monte Carlo","created":"2021-07-15","cited_by_count":4,"area":null},{"id":"2306.07159","title":"On the Computation-Communication Trade-Off with A Flexible Gradient Tracking Approach","created":"2023-06-12","cited_by_count":4,"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":"2209.10105","title":"Distributed Online Non-convex Optimization with Composite Regret","created":"2022-09-21","cited_by_count":2,"area":null},{"id":"2307.06620","title":"Online Distributed Learning with Quantized Finite-Time Coordination","created":"2023-07-13","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},{"id":"2407.01283","title":"Energy-Aware Decentralized Learning with Intermittent Model Training","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2508.08606","title":"Distributed optimization: designed for federated learning","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2309.02626","title":"Adaptive Consensus: A network pruning approach for decentralized optimization","created":"2023-09-06","cited_by_count":0,"area":null},{"id":"2311.03496","title":"Asynchronous Local Computations in Distributed Bayesian Learning","created":"2023-11-06","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":"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":"2509.18129","title":"Pareto-optimal Trade-offs Between Communication and Computation with Flexible Gradient Tracking","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2607.12172","title":"Decentralized Gradient Descent: Bottleneck Regimes and Budget Complexity","created":"2026-07-13","cited_by_count":0,"area":null}],"next_cursor":null}