{"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":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"2007.07481","title":"Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization","created":"2020-07-15","cited_by_count":906},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"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":"1909.13014","title":"FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization","created":"2019-09-28","cited_by_count":356},{"id":"1901.09847","title":"Error Feedback Fixes SignSGD and other Gradient Compression Schemes","created":"2019-01-28","cited_by_count":310},{"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":"1909.04746","title":"Tighter Theory for Local SGD on Identical and Heterogeneous Data","created":"2019-09-10","cited_by_count":266},{"id":"1809.10505","title":"The Convergence of Sparsified Gradient Methods","created":"2018-09-27","cited_by_count":229},{"id":"1612.01064","title":"Trained Ternary Quantization","created":"2016-12-04","cited_by_count":208},{"id":"1901.09401","title":"SGD: General Analysis and Improved Rates","created":"2019-01-27","cited_by_count":207},{"id":"1808.07217","title":"Don't Use Large Mini-Batches, Use Local SGD","created":"2018-08-22","cited_by_count":202},{"id":"1710.09854","title":"Gradient Sparsification for Communication-Efficient Distributed Optimization","created":"2017-10-26","cited_by_count":201},{"id":"1906.02367","title":"Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computations","created":"2019-06-06","cited_by_count":181},{"id":"2002.03329","title":"Better Theory for SGD in the Nonconvex World","created":"2020-02-09","cited_by_count":158},{"id":"1805.08114","title":"On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes","created":"2018-05-21","cited_by_count":156},{"id":"2002.07839","title":"Is Local SGD Better than Minibatch SGD?","created":"2020-02-18","cited_by_count":151},{"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":"2002.10542","title":"Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence","created":"2020-02-24","cited_by_count":137},{"id":"1806.04090","title":"ATOMO: Communication-efficient Learning via Atomic Sparsification","created":"2018-06-11","cited_by_count":136},{"id":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134},{"id":"1310.5715","title":"Stochastic Gradient Descent, Weighted Sampling, and the Randomized Kaczmarz algorithm","created":"2013-10-21","cited_by_count":133},{"id":"2106.05203","title":"EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback","created":"2021-06-09","cited_by_count":133},{"id":"2102.07053","title":"Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients","created":"2021-02-14","cited_by_count":123},{"id":"1506.08272","title":"Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization","created":"2015-06-27","cited_by_count":116},{"id":"2005.05238","title":"FedSplit: An algorithmic framework for fast federated optimization","created":"2020-05-11","cited_by_count":108},{"id":"1910.13598","title":"Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization","created":"2019-10-30","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":"1802.03801","title":"SGD and Hogwild! Convergence Without the Bounded Gradients Assumption","created":"2018-02-11","cited_by_count":95},{"id":"2011.02828","title":"Local SGD: Unified Theory and New Efficient Methods","created":"2020-11-03","cited_by_count":88},{"id":"1810.08313","title":"Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD","created":"2018-10-19","cited_by_count":77},{"id":"1806.08054","title":"Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization","created":"2018-06-21","cited_by_count":76},{"id":"1904.12838","title":"The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares","created":"2019-04-29","cited_by_count":68},{"id":"2007.13137","title":"Fast-Convergent Federated Learning","created":"2020-07-26","cited_by_count":61},{"id":"2010.12292","title":"Linearly Converging Error Compensated SGD","created":"2020-10-23","cited_by_count":61},{"id":"1507.01030","title":"Incremental Gradient, Subgradient, and Proximal Methods for Convex Optimization: A Survey","created":"2015-07-03","cited_by_count":45},{"id":"2006.11077","title":"A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning","created":"2020-06-19","cited_by_count":43},{"id":"1505.04824","title":"An Asynchronous Mini-Batch Algorithm for Regularized Stochastic Optimization","created":"2015-05-18","cited_by_count":38},{"id":"2111.03741","title":"Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective","created":"2021-11-05","cited_by_count":38},{"id":"2206.04723","title":"On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data","created":"2022-06-09","cited_by_count":38},{"id":"2206.05187","title":"On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyond","created":"2022-06-10","cited_by_count":38},{"id":"2204.03529","title":"FedADMM: A Robust Federated Deep Learning Framework with Adaptivity to System Heterogeneity","created":"2022-04-07","cited_by_count":25},{"id":"2102.09393","title":"On the Convergence of Step Decay Step-Size for Stochastic Optimization","created":"2021-02-18","cited_by_count":21},{"id":"2301.04935","title":"A Stochastic Proximal Polyak Step Size","created":"2023-01-12","cited_by_count":15},{"id":"2007.00534","title":"On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent","created":"2020-07-01","cited_by_count":11},{"id":"2008.05823","title":"Step-Ahead Error Feedback for Distributed Training with Compressed Gradient","created":"2020-08-13","cited_by_count":9},{"id":"2002.10597","title":"Statistical Adaptive Stochastic Gradient Methods","created":"2020-02-25","cited_by_count":8},{"id":"1909.10327","title":"Compressed Gradient Methods with Hessian-Aided Error Compensation","created":"2019-09-23","cited_by_count":6},{"id":"2208.11879","title":"A simplified convergence theory for Byzantine resilient stochastic gradient descent","created":"2022-08-25","cited_by_count":3}],"next_cursor":null}