{"list":"other","total":55,"rows":[{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"1705.09056","title":"Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent","created":"2017-05-25","cited_by_count":502},{"id":"2003.10422","title":"A Unified Theory of Decentralized SGD with Changing Topology and Local Updates","created":"2020-03-23","cited_by_count":367},{"id":"1807.06629","title":"Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning","created":"2018-07-17","cited_by_count":278},{"id":"1905.03817","title":"On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization","created":"2019-05-09","cited_by_count":180},{"id":"1404.6264","title":"EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization","created":"2014-04-24","cited_by_count":160},{"id":"1310.7063","title":"On the Convergence of Decentralized Gradient Descent","created":"2013-10-26","cited_by_count":159},{"id":"1803.06523","title":"Stochastic model-based minimization of weakly convex functions","created":"2018-03-17","cited_by_count":159},{"id":"1308.6594","title":"Mini-batch Stochastic Approximation Methods for Nonconvex Stochastic Composite Optimization","created":"2013-08-29","cited_by_count":143},{"id":"1803.07068","title":"D$^2$: Decentralized Training over Decentralized Data","created":"2018-03-19","cited_by_count":140},{"id":"2211.08413","title":"Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges","created":"2022-11-15","cited_by_count":138},{"id":"2007.07989","title":"An Improved Analysis of Stochastic Gradient Descent with Momentum","created":"2020-07-15","cited_by_count":119},{"id":"2104.11375","title":"Decentralized Federated Averaging","created":"2021-04-23","cited_by_count":114},{"id":"1805.11454","title":"Distributed Stochastic Gradient Tracking Methods","created":"2018-05-25","cited_by_count":106},{"id":"2311.06750","title":"Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark","created":"2023-11-12","cited_by_count":99},{"id":"2202.03836","title":"An Improved Analysis of Gradient Tracking for Decentralized Machine Learning","created":"2022-02-08","cited_by_count":69},{"id":"2307.04722","title":"Advances and Challenges in Meta-Learning: A Technical Review","created":"2023-07-10","cited_by_count":65},{"id":"1808.10396","title":"A Unified Analysis of Stochastic Momentum Methods for Deep Learning","created":"2018-08-30","cited_by_count":55},{"id":"2107.12048","title":"Decentralized Federated Learning: Balancing Communication and Computing Costs","created":"2021-07-26","cited_by_count":55},{"id":"2008.04195","title":"An improved convergence analysis for decentralized online stochastic non-convex optimization","created":"2020-08-10","cited_by_count":53},{"id":"2011.08474","title":"Federated Composite Optimization","created":"2020-11-17","cited_by_count":49},{"id":"2110.09993","title":"A Unified and Refined Convergence Analysis for Non-Convex Decentralized Learning","created":"2021-10-19","cited_by_count":44},{"id":"1608.05766","title":"On Nonconvex Decentralized Gradient Descent","created":"2016-08-20","cited_by_count":42},{"id":"2306.16504","title":"Momentum Benefits Non-IID Federated Learning Simply and Provably","created":"2023-06-28","cited_by_count":38},{"id":"2203.15104","title":"FedADMM: A Federated Primal-Dual Algorithm Allowing Partial Participation","created":"2022-03-28","cited_by_count":36},{"id":"1903.10956","title":"On the Influence of Bias-Correction on Distributed Stochastic Optimization","created":"2019-03-26","cited_by_count":34},{"id":"1802.04477","title":"A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimization","created":"2018-02-13","cited_by_count":33},{"id":"2002.05466","title":"Convergence of a Stochastic Gradient Method with Momentum for Non-Smooth Non-Convex Optimization","created":"2020-02-13","cited_by_count":32},{"id":"2301.01313","title":"Decentralized Gradient Tracking with Local Steps","created":"2023-01-03","cited_by_count":32},{"id":"2103.03452","title":"FedDR -- Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimization","created":"2021-03-05","cited_by_count":29},{"id":"2009.05837","title":"A general framework for decentralized optimization with first-order methods","created":"2020-09-12","cited_by_count":28},{"id":"2302.00620","title":"Local Exact-Diffusion for Decentralized Optimization and Learning","created":"2023-02-01","cited_by_count":24},{"id":"2308.00522","title":"Efficient Federated Learning via Local Adaptive Amended Optimizer with Linear Speedup","created":"2023-07-30","cited_by_count":23},{"id":"2210.04757","title":"On the Performance of Gradient Tracking with Local Updates","created":"2022-10-10","cited_by_count":21},{"id":"2209.15505","title":"Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data","created":"2022-09-30","cited_by_count":20},{"id":"1808.02942","title":"Distributed heavy-ball: A generalization and acceleration of first-order methods with gradient tracking","created":"2018-08-08","cited_by_count":14},{"id":"2205.06491","title":"Tighter Regret Analysis and Optimization of Online Federated Learning","created":"2022-05-13","cited_by_count":14},{"id":"2003.07612","title":"Variable Smoothing for Weakly Convex Composite Functions","created":"2020-03-17","cited_by_count":12},{"id":"2207.08204","title":"Fast Composite Optimization and Statistical Recovery in Federated Learning","created":"2022-07-17","cited_by_count":12},{"id":"2305.04792","title":"Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data","created":"2023-05-08","cited_by_count":12},{"id":"2110.01594","title":"A Stochastic Proximal Gradient Framework for Decentralized Non-Convex Composite Optimization: Topology-Independent Sample Complexity and Communication Efficiency","created":"2021-10-04","cited_by_count":11},{"id":"2302.14252","title":"Compressed Decentralized Proximal Stochastic Gradient Method for Nonconvex Composite Problems with Heterogeneous Data","created":"2023-02-28","cited_by_count":11},{"id":"2211.11954","title":"Proximal Stochastic Recursive Momentum Methods for Nonconvex Composite Decentralized Optimization","created":"2022-11-22","cited_by_count":10},{"id":"2403.02967","title":"Non-convex Stochastic Composite Optimization with Polyak Momentum","created":"2024-03-05","cited_by_count":9},{"id":"2011.05082","title":"Distributed Stochastic Consensus Optimization with Momentum for Nonconvex Nonsmooth Problems","created":"2020-11-10","cited_by_count":8},{"id":"2306.02570","title":"When Decentralized Optimization Meets Federated Learning","created":"2023-06-05","cited_by_count":7},{"id":"2309.01795","title":"Composite federated learning with heterogeneous data","created":"2023-09-04","cited_by_count":7},{"id":"1605.07747","title":"NESTT: A Nonconvex Primal-Dual Splitting Method for Distributed and Stochastic Optimization","created":"2016-05-25","cited_by_count":5},{"id":"2205.14811","title":"Last-iterate convergence analysis of stochastic momentum methods for neural networks","created":"2022-05-30","cited_by_count":5},{"id":"2402.08821","title":"Problem-Parameter-Free Decentralized Nonconvex Stochastic Optimization","created":"2024-02-13","cited_by_count":5},{"id":"2302.09766","title":"A One-Sample Decentralized Proximal Algorithm for Non-Convex Stochastic Composite Optimization","created":"2023-02-20","cited_by_count":4},{"id":"1802.03284","title":"Mini-Batch Stochastic ADMMs for Nonconvex Nonsmooth Optimization","created":"2018-02-08","cited_by_count":3},{"id":"2402.09714","title":"An Accelerated Distributed Stochastic Gradient Method with Momentum","created":"2024-02-15","cited_by_count":3}],"next_cursor":null}