{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"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":"1905.12022","title":"Bayesian Nonparametric Federated Learning of Neural Networks","created":"2019-05-28","cited_by_count":387},{"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":"1912.02365","title":"Lower Bounds for Non-Convex Stochastic Optimization","created":"2019-12-05","cited_by_count":307},{"id":"1807.01695","title":"SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path Integrated Differential Estimator","created":"2018-07-04","cited_by_count":287},{"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":"1710.06952","title":"Asynchronous Decentralized Parallel Stochastic Gradient Descent","created":"2017-10-18","cited_by_count":159},{"id":"1811.10792","title":"Stochastic Gradient Push for Distributed Deep Learning","created":"2018-11-27","cited_by_count":152},{"id":"1607.03218","title":"Achieving Geometric Convergence for Distributed Optimization over Time-Varying Graphs","created":"2016-07-12","cited_by_count":150},{"id":"1803.07068","title":"D$^2$: Decentralized Training over Decentralized Data","created":"2018-03-19","cited_by_count":140},{"id":"1710.11606","title":"Lower Bounds for Finding Stationary Points I","created":"2017-10-31","cited_by_count":126},{"id":"1709.08765","title":"Network Topology and Communication-Computation Tradeoffs in Decentralized Optimization","created":"2017-09-26","cited_by_count":122},{"id":"1602.00591","title":"NEXT: In-Network Nonconvex Optimization","created":"2016-02-01","cited_by_count":107},{"id":"1905.05957","title":"DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression","created":"2019-05-15","cited_by_count":99},{"id":"1702.08704","title":"Optimal algorithms for smooth and strongly convex distributed optimization in networks","created":"2017-02-28","cited_by_count":83},{"id":"1303.2289","title":"Distributed optimization over time-varying directed graphs","created":"2013-03-10","cited_by_count":78},{"id":"2102.04761","title":"Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data","created":"2021-02-09","cited_by_count":69},{"id":"2202.03836","title":"An Improved Analysis of Gradient Tracking for Decentralized Machine Learning","created":"2022-02-08","cited_by_count":69},{"id":"1905.09435","title":"MATCHA: Speeding Up Decentralized SGD via Matching Decomposition Sampling","created":"2019-05-23","cited_by_count":67},{"id":"1904.05115","title":"Stochastic Distributed Learning with Gradient Quantization and Variance Reduction","created":"2019-04-10","cited_by_count":65},{"id":"2006.08085","title":"Optimal Complexity in Decentralized Training","created":"2020-06-15","cited_by_count":60},{"id":"1711.00841","title":"Lower Bounds for Finding Stationary Points II: First-Order Methods","created":"2017-11-02","cited_by_count":58},{"id":"1307.5561","title":"On the Linear Convergence of the ADMM in Decentralized Consensus Optimization","created":"2013-07-21","cited_by_count":57},{"id":"1801.02982","title":"How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD","created":"2018-01-08","cited_by_count":57},{"id":"2110.13363","title":"Exponential Graph is Provably Efficient for Decentralized Deep Training","created":"2021-10-26","cited_by_count":56},{"id":"2008.04195","title":"An improved convergence analysis for decentralized online stochastic non-convex optimization","created":"2020-08-10","cited_by_count":53},{"id":"1704.07807","title":"A decentralized proximal-gradient method with network independent step-sizes and separated convergence rates","created":"2017-04-25","cited_by_count":51},{"id":"1702.05122","title":"Exact Diffusion for Distributed Optimization and Learning --- Part I: Algorithm Development","created":"2017-02-16","cited_by_count":50},{"id":"2110.09993","title":"A Unified and Refined Convergence Analysis for Non-Convex Decentralized Learning","created":"2021-10-19","cited_by_count":44},{"id":"2006.11773","title":"Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization","created":"2020-06-21","cited_by_count":43},{"id":"1806.00291","title":"Optimal Algorithms for Non-Smooth Distributed Optimization in Networks","created":"2018-06-01","cited_by_count":41},{"id":"2104.11981","title":"DecentLaM: Decentralized Momentum SGD for Large-batch Deep Training","created":"2021-04-24","cited_by_count":40},{"id":"1507.02000","title":"An optimal randomized incremental gradient method","created":"2015-07-08","cited_by_count":33},{"id":"2206.03665","title":"Lower Bounds and Nearly Optimal Algorithms in Distributed Learning with Communication Compression","created":"2022-06-08","cited_by_count":33},{"id":"1901.09109","title":"DADAM: A Consensus-based Distributed Adaptive Gradient Method for Online Optimization","created":"2019-01-25","cited_by_count":30},{"id":"2105.08023","title":"Removing Data Heterogeneity Influence Enhances Network Topology Dependence of Decentralized SGD","created":"2021-05-17","cited_by_count":29},{"id":"1809.00710","title":"A Dual Approach for Optimal Algorithms in Distributed Optimization over Networks","created":"2018-09-03","cited_by_count":27},{"id":"2105.09080","title":"Accelerating Gossip SGD with Periodic Global Averaging","created":"2021-05-19","cited_by_count":25},{"id":"2106.04469","title":"Lower Bounds and Optimal Algorithms for Smooth and Strongly Convex Decentralized Optimization Over Time-Varying Networks","created":"2021-06-08","cited_by_count":19},{"id":"1811.01903","title":"Lower Bounds for Parallel and Randomized Convex Optimization","created":"2018-11-05","cited_by_count":17},{"id":"2009.11069","title":"Towards accelerated rates for distributed optimization over time-varying networks","created":"2020-09-23","cited_by_count":10},{"id":"1804.02729","title":"Distributed Non-Convex First-Order Optimization and Information Processing: Lower Complexity Bounds and Rate Optimal Algorithms","created":"2018-04-08","cited_by_count":6},{"id":"2103.15598","title":"An Accelerated Method For Decentralized Distributed Stochastic Optimization Over Time-Varying Graphs","created":"2021-03-29","cited_by_count":6},{"id":"1703.09180","title":"Gradient Method With Inexact Oracle for Composite Non-Convex Optimization","created":"2017-03-27","cited_by_count":4},{"id":"2209.07729","title":"On Weighted Graph Sparsification by Linear Sketching","created":"2022-09-16","cited_by_count":3}],"next_cursor":null}