{"list":"other","total":67,"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":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"1812.00564","title":"Split learning for health: Distributed deep learning without sharing raw patient data","created":"2018-12-03","cited_by_count":395},{"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":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315},{"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":"1703.00102","title":"SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient","created":"2017-03-01","cited_by_count":220},{"id":"1901.09401","title":"SGD: General Analysis and Improved Rates","created":"2019-01-27","cited_by_count":207},{"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":"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":"1910.06378","title":"SCAFFOLD: Stochastic Controlled Averaging for Federated Learning","created":"2019-10-14","cited_by_count":175},{"id":"2007.01154","title":"Federated Learning with Compression: Unified Analysis and Sharp Guarantees","created":"2020-07-02","cited_by_count":160},{"id":"2002.03329","title":"Better Theory for SGD in the Nonconvex World","created":"2020-02-09","cited_by_count":158},{"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":"2108.10749","title":"Federated Learning for Open Banking","created":"2021-08-24","cited_by_count":141},{"id":"2009.13012","title":"Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges","created":"2020-09-28","cited_by_count":139},{"id":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134},{"id":"2010.13723","title":"Optimal Client Sampling for Federated Learning","created":"2020-10-26","cited_by_count":124},{"id":"2102.07053","title":"Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients","created":"2021-02-14","cited_by_count":123},{"id":"2008.10898","title":"PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization","created":"2020-08-25","cited_by_count":119},{"id":"1901.09269","title":"Distributed Learning with Compressed Gradient Differences","created":"2019-01-26","cited_by_count":112},{"id":"1905.05957","title":"DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression","created":"2019-05-15","cited_by_count":99},{"id":"2105.05883","title":"Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning","created":"2021-05-12","cited_by_count":93},{"id":"2002.11364","title":"Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization","created":"2020-02-26","cited_by_count":90},{"id":"2011.02828","title":"Local SGD: Unified Theory and New Efficient Methods","created":"2020-11-03","cited_by_count":88},{"id":"1905.11261","title":"A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent","created":"2019-05-27","cited_by_count":84},{"id":"1909.04715","title":"First Analysis of Local GD on Heterogeneous Data","created":"2019-09-10","cited_by_count":81},{"id":"2004.01442","title":"From Local SGD to Local Fixed-Point Methods for Federated Learning","created":"2020-04-03","cited_by_count":74},{"id":"2106.07820","title":"On Large-Cohort Training for Federated Learning","created":"2021-06-15","cited_by_count":74},{"id":"1904.05115","title":"Stochastic Distributed Learning with Gradient Quantization and Variance Reduction","created":"2019-04-10","cited_by_count":65},{"id":"1806.06573","title":"Distributed learning with compressed gradients","created":"2018-06-18","cited_by_count":55},{"id":"2011.01697","title":"A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free!","created":"2020-11-03","cited_by_count":42},{"id":"2011.08756","title":"Stochastic Client Selection for Federated Learning with Volatile Clients","created":"2020-11-17","cited_by_count":39},{"id":"2105.07066","title":"Node Selection Toward Faster Convergence for Federated Learning on Non-IID Data","created":"2021-05-14","cited_by_count":39},{"id":"2106.03328","title":"Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learning","created":"2021-06-07","cited_by_count":39},{"id":"2111.03741","title":"Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective","created":"2021-11-05","cited_by_count":38},{"id":"2007.00878","title":"On the Outsized Importance of Learning Rates in Local Update Methods","created":"2020-07-02","cited_by_count":36},{"id":"2207.04338","title":"Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning","created":"2022-07-09","cited_by_count":33},{"id":"2110.03300","title":"Permutation Compressors for Provably Faster Distributed Nonconvex Optimization","created":"2021-10-07","cited_by_count":32},{"id":"2302.03109","title":"On the Convergence of Federated Averaging with Cyclic Client Participation","created":"2023-02-06","cited_by_count":31},{"id":"2207.12891","title":"RandProx: Primal-Dual Optimization Algorithms with Randomized Proximal Updates","created":"2022-07-26","cited_by_count":28},{"id":"2201.11066","title":"Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization","created":"2022-01-26","cited_by_count":23},{"id":"2212.14370","title":"Can 5th Generation Local Training Methods Support Client Sampling? Yes!","created":"2022-12-29","cited_by_count":22},{"id":"2102.07245","title":"Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization","created":"2021-02-14","cited_by_count":21},{"id":"1705.07261","title":"Stochastic Recursive Gradient Algorithm for Nonconvex Optimization","created":"2017-05-20","cited_by_count":20},{"id":"2009.02388","title":"On Communication Compression for Distributed Optimization on Heterogeneous Data","created":"2020-09-04","cited_by_count":19},{"id":"2104.09342","title":"Random Reshuffling with Variance Reduction: New Analysis and Better Rates","created":"2021-04-19","cited_by_count":19},{"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":"2206.07021","title":"Federated Optimization Algorithms with Random Reshuffling and Gradient Compression","created":"2022-06-14","cited_by_count":18},{"id":"2210.16402","title":"GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity","created":"2022-10-28","cited_by_count":18},{"id":"2106.03056","title":"MURANA: A Generic Framework for Stochastic Variance-Reduced Optimization","created":"2021-06-06","cited_by_count":14},{"id":"2302.03662","title":"Federated Learning with Regularized Client Participation","created":"2023-02-07","cited_by_count":14},{"id":"1511.06051","title":"SparkNet: Training Deep Networks in Spark","created":"2015-11-19","cited_by_count":13},{"id":"2205.03914","title":"Federated Random Reshuffling with Compression and Variance Reduction","created":"2022-05-08","cited_by_count":12},{"id":"1909.04716","title":"Gradient Descent with Compressed Iterates","created":"2019-09-10","cited_by_count":11},{"id":"1912.09925","title":"Distributed Fixed Point Methods with Compressed Iterates","created":"2019-12-20","cited_by_count":11},{"id":"2210.13277","title":"CompressedScaffnew: The First Theoretical Double Acceleration of Communication from Local Training and Compression in Distributed Optimization","created":"2022-10-24","cited_by_count":11},{"id":"2206.02275","title":"Sharper Rates and Flexible Framework for Nonconvex SGD with Client and Data Sampling","created":"2022-06-05","cited_by_count":10}],"next_cursor":null}