{"list":"other","total":54,"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":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"2007.07481","title":"Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization","created":"2020-07-15","cited_by_count":906},{"id":"1909.06335","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","created":"2019-09-13","cited_by_count":851},{"id":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"1811.03604","title":"Federated Learning for Mobile Keyboard Prediction","created":"2018-11-08","cited_by_count":572},{"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":"2003.10422","title":"A Unified Theory of Decentralized SGD with Changing Topology and Local Updates","created":"2020-03-23","cited_by_count":367},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315},{"id":"2003.00307","title":"Loss landscapes and optimization in over-parameterized non-linear systems and neural networks","created":"2020-02-29","cited_by_count":233},{"id":"1702.05373","title":"EMNIST: an extension of MNIST to handwritten letters","created":"2017-02-17","cited_by_count":213},{"id":"1812.02903","title":"Applied Federated Learning: Improving Google Keyboard Query Suggestions","created":"2018-12-07","cited_by_count":204},{"id":"2010.01243","title":"Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies","created":"2020-10-03","cited_by_count":198},{"id":"2101.11203","title":"Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning","created":"2021-01-27","cited_by_count":193},{"id":"1906.02367","title":"Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computations","created":"2019-06-06","cited_by_count":181},{"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":"1611.04482","title":"Practical Secure Aggregation for Federated Learning on User-Held Data","created":"2016-11-14","cited_by_count":178},{"id":"1910.06378","title":"SCAFFOLD: Stochastic Controlled Averaging for Federated Learning","created":"2019-10-14","cited_by_count":175},{"id":"2103.00039","title":"Practical and Private (Deep) Learning without Sampling or Shuffling","created":"2021-02-26","cited_by_count":170},{"id":"1910.14425","title":"On the Convergence of Local Descent Methods in Federated Learning","created":"2019-10-31","cited_by_count":153},{"id":"2002.07839","title":"Is Local SGD Better than Minibatch SGD?","created":"2020-02-18","cited_by_count":151},{"id":"2006.04735","title":"Minibatch vs Local SGD for Heterogeneous Distributed Learning","created":"2020-06-08","cited_by_count":147},{"id":"1910.00643","title":"SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum","created":"2019-10-01","cited_by_count":121},{"id":"2006.05988","title":"Random Reshuffling: Simple Analysis with Vast Improvements","created":"2020-06-10","cited_by_count":115},{"id":"1910.13598","title":"Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization","created":"2019-10-30","cited_by_count":107},{"id":"2111.04877","title":"Papaya: Practical, Private, and Scalable Federated Learning","created":"2021-11-08","cited_by_count":90},{"id":"2102.08503","title":"Federated Evaluation and Tuning for On-Device Personalization: System Design & Applications","created":"2021-02-16","cited_by_count":85},{"id":"1510.08560","title":"Why Random Reshuffling Beats Stochastic Gradient Descent","created":"2015-10-29","cited_by_count":79},{"id":"2006.10311","title":"SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolation","created":"2020-06-18","cited_by_count":67},{"id":"2006.06954","title":"Towards Flexible Device Participation in Federated Learning","created":"2020-06-12","cited_by_count":65},{"id":"1908.00045","title":"How Good is SGD with Random Shuffling?","created":"2019-07-31","cited_by_count":64},{"id":"2207.14130","title":"FedVARP: Tackling the Variance Due to Partial Client Participation in Federated Learning","created":"2022-07-28","cited_by_count":64},{"id":"1909.12641","title":"Active Federated Learning","created":"2019-09-27","cited_by_count":63},{"id":"1903.01463","title":"SGD without Replacement: Sharper Rates for General Smooth Convex Functions","created":"2019-03-04","cited_by_count":61},{"id":"2002.08246","title":"A Unified Convergence Analysis for Shuffling-Type Gradient Methods","created":"2020-02-19","cited_by_count":58},{"id":"2006.06946","title":"SGD with shuffling: optimal rates without component convexity and large epoch requirements","created":"2020-06-12","cited_by_count":58},{"id":"2002.10400","title":"Closing the convergence gap of SGD without replacement","created":"2020-02-24","cited_by_count":57},{"id":"2211.06530","title":"Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning","created":"2022-11-12","cited_by_count":48},{"id":"2205.13648","title":"A Unified Analysis of Federated Learning with Arbitrary Client Participation","created":"2022-05-26","cited_by_count":45},{"id":"1904.10120","title":"Semi-Cyclic Stochastic Gradient Descent","created":"2019-04-23","cited_by_count":40},{"id":"2007.06605","title":"Privacy Amplification via Random Check-Ins","created":"2020-07-13","cited_by_count":39},{"id":"2206.04723","title":"On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data","created":"2022-06-09","cited_by_count":38},{"id":"2110.10342","title":"Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond","created":"2021-10-20","cited_by_count":36},{"id":"1510.08562","title":"Convergence Rate of Incremental Gradient and Newton Methods","created":"2015-10-29","cited_by_count":27},{"id":"2104.09342","title":"Random Reshuffling with Variance Reduction: New Analysis and Better Rates","created":"2021-04-19","cited_by_count":19},{"id":"2106.06880","title":"Random Shuffling Beats SGD Only After Many Epochs on Ill-Conditioned Problems","created":"2021-06-12","cited_by_count":17},{"id":"2110.04926","title":"Convergence of Random Reshuffling Under The Kurdyka-{\\L}ojasiewicz Inequality","created":"2021-10-10","cited_by_count":16},{"id":"2210.17073","title":"Communication-Efficient Local SGD with Age-Based Worker Selection","created":"2022-10-31","cited_by_count":3}],"next_cursor":null}