{"list":"other","total":56,"rows":[{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"1806.00582","title":"Federated Learning with Non-IID Data","created":"2018-06-02","cited_by_count":1108},{"id":"1610.02527","title":"Federated Optimization: Distributed Machine Learning for On-Device Intelligence","created":"2016-10-08","cited_by_count":564},{"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":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"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":"1906.00331","title":"On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems","created":"2019-06-02","cited_by_count":270},{"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":"1811.10792","title":"Stochastic Gradient Push for Distributed Deep Learning","created":"2018-11-27","cited_by_count":152},{"id":"2002.07839","title":"Is Local SGD Better than Minibatch SGD?","created":"2020-02-18","cited_by_count":151},{"id":"1607.03218","title":"Achieving Geometric Convergence for Distributed Optimization over Time-Varying Graphs","created":"2016-07-12","cited_by_count":150},{"id":"2006.04735","title":"Minibatch vs Local SGD for Heterogeneous Distributed Learning","created":"2020-06-08","cited_by_count":147},{"id":"2005.11418","title":"FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Data","created":"2020-05-22","cited_by_count":144},{"id":"1803.07068","title":"D$^2$: Decentralized Training over Decentralized Data","created":"2018-03-19","cited_by_count":140},{"id":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134},{"id":"1805.11454","title":"Distributed Stochastic Gradient Tracking Methods","created":"2018-05-25","cited_by_count":106},{"id":"2308.08165","title":"Stochastic Controlled Averaging for Federated Learning with Communication Compression","created":"2023-08-16","cited_by_count":101},{"id":"1702.08704","title":"Optimal algorithms for smooth and strongly convex distributed optimization in networks","created":"2017-02-28","cited_by_count":83},{"id":"1907.04232","title":"Unified Optimal Analysis of the (Stochastic) Gradient Method","created":"2019-07-09","cited_by_count":82},{"id":"1912.12844","title":"Variance Reduced Local SGD with Lower Communication Complexity","created":"2019-12-30","cited_by_count":80},{"id":"1303.2289","title":"Distributed optimization over time-varying directed graphs","created":"2013-03-10","cited_by_count":78},{"id":"1808.02901","title":"Lower complexity bounds of first-order methods for convex-concave bilinear saddle-point problems","created":"2018-08-08","cited_by_count":76},{"id":"2202.03836","title":"An Improved Analysis of Gradient Tracking for Decentralized Machine Learning","created":"2022-02-08","cited_by_count":69},{"id":"2006.08085","title":"Optimal Complexity in Decentralized Training","created":"2020-06-15","cited_by_count":60},{"id":"1307.5561","title":"On the Linear Convergence of the ADMM in Decentralized Consensus Optimization","created":"2013-07-21","cited_by_count":57},{"id":"2008.04195","title":"An improved convergence analysis for decentralized online stochastic non-convex optimization","created":"2020-08-10","cited_by_count":53},{"id":"1702.05122","title":"Exact Diffusion for Distributed Optimization and Learning --- Part I: Algorithm Development","created":"2017-02-16","cited_by_count":50},{"id":"2112.05604","title":"Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity","created":"2021-12-10","cited_by_count":49},{"id":"2006.11773","title":"Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization","created":"2020-06-21","cited_by_count":43},{"id":"1712.05654","title":"Catalyst Acceleration for First-order Convex Optimization: from Theory to Practice","created":"2017-12-15","cited_by_count":39},{"id":"2306.16504","title":"Momentum Benefits Non-IID Federated Learning Simply and Provably","created":"2023-06-28","cited_by_count":38},{"id":"2301.01313","title":"Decentralized Gradient Tracking with Local Steps","created":"2023-01-03","cited_by_count":32},{"id":"2102.01583","title":"The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication","created":"2021-02-02","cited_by_count":31},{"id":"2102.09468","title":"Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization","created":"2021-02-18","cited_by_count":31},{"id":"1802.01504","title":"Linear Convergence of the Primal-Dual Gradient Method for Convex-Concave Saddle Point Problems without Strong Convexity","created":"2018-02-05","cited_by_count":29},{"id":"2207.12891","title":"RandProx: Primal-Dual Optimization Algorithms with Randomized Proximal Updates","created":"2022-07-26","cited_by_count":28},{"id":"1809.00710","title":"A Dual Approach for Optimal Algorithms in Distributed Optimization over Networks","created":"2018-09-03","cited_by_count":27},{"id":"2007.13605","title":"Alternating proximal-gradient steps for (stochastic) nonconvex-concave minimax problems","created":"2020-07-27","cited_by_count":26},{"id":"2302.00620","title":"Local Exact-Diffusion for Decentralized Optimization and Learning","created":"2023-02-01","cited_by_count":24},{"id":"1402.6065","title":"Multi-Agent Distributed Optimization via Inexact Consensus ADMM","created":"2014-02-25","cited_by_count":21},{"id":"2207.03957","title":"Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with Inexact Prox","created":"2022-07-08","cited_by_count":19},{"id":"2110.05282","title":"Optimal Gradient Tracking for Decentralized Optimization","created":"2021-10-11","cited_by_count":18},{"id":"1512.09295","title":"Strategies and Principles of Distributed Machine Learning on Big Data","created":"2015-12-31","cited_by_count":16},{"id":"1601.00194","title":"Convergence Rate of Distributed ADMM over Networks","created":"2016-01-02","cited_by_count":16},{"id":"1506.04216","title":"DSA: Decentralized Double Stochastic Averaging Gradient Algorithm","created":"2015-06-13","cited_by_count":14},{"id":"1512.08122","title":"Distributed Linearized Alternating Direction Method of Multipliers for Composite Convex Consensus Optimization","created":"2015-12-26","cited_by_count":13},{"id":"2002.10110","title":"Revisiting EXTRA for Smooth Distributed Optimization","created":"2020-02-24","cited_by_count":12},{"id":"1307.8254","title":"On the O(1/k) Convergence of Asynchronous Distributed Alternating Direction Method of Multipliers","created":"2013-07-31","cited_by_count":11},{"id":"1910.08701","title":"Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks","created":"2019-10-19","cited_by_count":9},{"id":"1910.10666","title":"Accelerated Primal-Dual Algorithms for Distributed Smooth Convex Optimization over Networks","created":"2019-10-23","cited_by_count":7},{"id":"1511.08905","title":"Stochastic Proximal Gradient Consensus Over Random Networks","created":"2015-11-28","cited_by_count":5},{"id":"2310.17759","title":"Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization","created":"2023-10-26","cited_by_count":3},{"id":"2305.10294","title":"DualFL: A Duality-based Federated Learning Algorithm with Communication Acceleration in the General Convex Regime","created":"2023-05-17","cited_by_count":2},{"id":"2311.02814","title":"A Novel Catalyst Scheme for Stochastic Minimax Optimization","created":"2023-11-06","cited_by_count":2}],"next_cursor":null}