{"list":"other","total":51,"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":"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":"1909.06335","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","created":"2019-09-13","cited_by_count":851},{"id":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"id":"1705.10467","title":"Federated Multi-Task Learning","created":"2017-05-30","cited_by_count":672},{"id":"2006.08848","title":"Personalized Federated Learning with Moreau Envelopes","created":"2020-06-16","cited_by_count":618},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"1902.00146","title":"Agnostic Federated Learning","created":"2019-02-01","cited_by_count":456},{"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":"2003.13461","title":"Adaptive Personalized Federated Learning","created":"2020-03-30","cited_by_count":358},{"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":"2010.01264","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","created":"2020-10-03","cited_by_count":337},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315},{"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":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","cited_by_count":273},{"id":"1909.12488","title":"Improving Federated Learning Personalization via Model Agnostic Meta Learning","created":"2019-09-27","cited_by_count":269},{"id":"1909.04746","title":"Tighter Theory for Local SGD on Identical and Heterogeneous Data","created":"2019-09-10","cited_by_count":266},{"id":"2002.05516","title":"Federated Learning of a Mixture of Global and Local Models","created":"2020-02-10","cited_by_count":210},{"id":"1808.07217","title":"Don't Use Large Mini-Batches, Use Local SGD","created":"2018-08-22","cited_by_count":202},{"id":"1511.03575","title":"Federated Optimization:Distributed Optimization Beyond the Datacenter","created":"2015-11-11","cited_by_count":195},{"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":"2009.01974","title":"FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning","created":"2020-09-04","cited_by_count":176},{"id":"1802.07876","title":"Federated Meta-Learning with Fast Convergence and Efficient Communication","created":"2018-02-22","cited_by_count":155},{"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":"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":"1904.09080","title":"Implicit regularization for deep neural networks driven by an Ornstein-Uhlenbeck like process","created":"2019-04-19","cited_by_count":123},{"id":"2010.02372","title":"Lower Bounds and Optimal Algorithms for Personalized Federated Learning","created":"2020-10-05","cited_by_count":123},{"id":"2106.06530","title":"Label Noise SGD Provably Prefers Flat Global Minimizers","created":"2021-06-11","cited_by_count":121},{"id":"2005.05238","title":"FedSplit: An algorithmic framework for fast federated optimization","created":"2020-05-11","cited_by_count":108},{"id":"2107.00233","title":"FedMix: Approximation of Mixup under Mean Augmented Federated Learning","created":"2021-07-01","cited_by_count":108},{"id":"1808.07576","title":"Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms","created":"2018-08-22","cited_by_count":106},{"id":"1708.01012","title":"On the convergence properties of a $K$-step averaging stochastic gradient descent algorithm for nonconvex optimization","created":"2017-08-03","cited_by_count":92},{"id":"1709.01953","title":"Implicit Regularization in Deep Learning","created":"2017-09-06","cited_by_count":90},{"id":"1707.06386","title":"Bridging the Gap between Constant Step Size Stochastic Gradient Descent and Markov Chains","created":"2017-07-20","cited_by_count":88},{"id":"2006.08950","title":"Federated Accelerated Stochastic Gradient Descent","created":"2020-06-16","cited_by_count":85},{"id":"1912.12844","title":"Variance Reduced Local SGD with Lower Communication Complexity","created":"2019-12-30","cited_by_count":80},{"id":"2010.05273","title":"Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithms","created":"2020-10-11","cited_by_count":78},{"id":"2110.14216","title":"What Do We Mean by Generalization in Federated Learning?","created":"2021-10-27","cited_by_count":62},{"id":"2011.08474","title":"Federated Composite Optimization","created":"2020-11-17","cited_by_count":49},{"id":"2007.00878","title":"On the Outsized Importance of Learning Rates in Local Update Methods","created":"2020-07-02","cited_by_count":36},{"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":"1906.01736","title":"Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms","created":"2019-06-04","cited_by_count":29},{"id":"2003.12880","title":"Federated Residual Learning","created":"2020-03-28","cited_by_count":23},{"id":"1407.2724","title":"On the Optimality of Averaging in Distributed Statistical Learning","created":"2014-07-10","cited_by_count":15},{"id":"1905.04346","title":"On the Computation and Communication Complexity of Parallel SGD with Dynamic Batch Sizes for Stochastic Non-Convex Optimization","created":"2019-05-10","cited_by_count":15},{"id":"2109.00534","title":"The Minimax Complexity of Distributed Optimization","created":"2021-09-01","cited_by_count":7}],"next_cursor":null}