{"list":"other","total":68,"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":"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":"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":"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":"1812.01097","title":"LEAF: A Benchmark for Federated Settings","created":"2018-12-03","cited_by_count":792},{"id":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"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":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"1407.0202","title":"SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives","created":"2014-07-01","cited_by_count":402},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","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":"2010.01264","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","created":"2020-10-03","cited_by_count":337},{"id":"1901.09847","title":"Error Feedback Fixes SignSGD and other Gradient Compression Schemes","created":"2019-01-28","cited_by_count":310},{"id":"1905.10018","title":"Momentum-Based Variance Reduction in Non-Convex SGD","created":"2019-05-24","cited_by_count":306},{"id":"1910.00189","title":"The Non-IID Data Quagmire of Decentralized Machine Learning","created":"2019-10-01","cited_by_count":305},{"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":"1705.07878","title":"TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning","created":"2017-05-22","cited_by_count":256},{"id":"1905.13727","title":"PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization","created":"2019-05-31","cited_by_count":238},{"id":"1809.10505","title":"The Convergence of Sparsified Gradient Methods","created":"2018-09-27","cited_by_count":229},{"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":"2102.13451","title":"FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout","created":"2021-02-26","cited_by_count":192},{"id":"2106.06639","title":"Federated Learning with Buffered Asynchronous Aggregation","created":"2021-06-11","cited_by_count":190},{"id":"1910.06378","title":"SCAFFOLD: Stochastic Controlled Averaging for Federated Learning","created":"2019-10-14","cited_by_count":175},{"id":"1812.07210","title":"Expanding the Reach of Federated Learning by Reducing Client Resource Requirements","created":"2018-12-18","cited_by_count":163},{"id":"2008.03606","title":"Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning","created":"2020-08-08","cited_by_count":154},{"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":"1610.02132","title":"QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding","created":"2016-10-07","cited_by_count":147},{"id":"2006.04735","title":"Minibatch vs Local SGD for Heterogeneous Distributed Learning","created":"2020-06-08","cited_by_count":147},{"id":"1611.00429","title":"Distributed Mean Estimation with Limited Communication","created":"2016-11-02","cited_by_count":136},{"id":"1806.04090","title":"ATOMO: Communication-efficient Learning via Atomic Sparsification","created":"2018-06-11","cited_by_count":136},{"id":"2106.05203","title":"EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback","created":"2021-06-09","cited_by_count":133},{"id":"2010.13723","title":"Optimal Client Sampling for Federated Learning","created":"2020-10-26","cited_by_count":124},{"id":"2006.05988","title":"Random Reshuffling: Simple Analysis with Vast Improvements","created":"2020-06-10","cited_by_count":115},{"id":"1901.09269","title":"Distributed Learning with Compressed Gradient Differences","created":"2019-01-26","cited_by_count":112},{"id":"1910.13598","title":"Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization","created":"2019-10-30","cited_by_count":107},{"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":"1905.10988","title":"Natural Compression for Distributed Deep Learning","created":"2019-05-27","cited_by_count":90},{"id":"2111.04877","title":"Papaya: Practical, Private, and Scalable Federated Learning","created":"2021-11-08","cited_by_count":90},{"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":"1907.04232","title":"Unified Optimal Analysis of the (Stochastic) Gradient Method","created":"2019-07-09","cited_by_count":82},{"id":"1909.04715","title":"First Analysis of Local GD on Heterogeneous Data","created":"2019-09-10","cited_by_count":81},{"id":"1912.12844","title":"Variance Reduced Local SGD with Lower Communication Complexity","created":"2019-12-30","cited_by_count":80},{"id":"1510.08560","title":"Why Random Reshuffling Beats Stochastic Gradient Descent","created":"2015-10-29","cited_by_count":79},{"id":"2102.07845","title":"MARINA: Faster Non-Convex Distributed Learning with Compression","created":"2021-02-15","cited_by_count":78},{"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":"1506.01900","title":"Communication Complexity of Distributed Convex Learning and Optimization","created":"2015-06-05","cited_by_count":60},{"id":"1905.12938","title":"Stochastic Sign Descent Methods: New Algorithms and Better Theory","created":"2019-05-30","cited_by_count":49},{"id":"2006.11077","title":"A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning","created":"2020-06-19","cited_by_count":43},{"id":"2108.00951","title":"Rethinking gradient sparsification as total error minimization","created":"2021-08-02","cited_by_count":41},{"id":"2110.10342","title":"Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond","created":"2021-10-20","cited_by_count":36},{"id":"1805.10222","title":"Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization","created":"2018-05-25","cited_by_count":34},{"id":"2102.06704","title":"Proximal and Federated Random Reshuffling","created":"2021-02-12","cited_by_count":33},{"id":"1905.05920","title":"Hybrid Stochastic Gradient Descent Algorithms for Stochastic Nonconvex Optimization","created":"2019-05-15","cited_by_count":32},{"id":"1911.09030","title":"Local AdaAlter: Communication-Efficient Stochastic Gradient Descent with Adaptive Learning Rates","created":"2019-11-20","cited_by_count":26},{"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":"2102.12528","title":"Preserved central model for faster bidirectional compression in distributed settings","created":"2021-02-24","cited_by_count":21},{"id":"1809.04146","title":"Nonconvex Variance Reduced Optimization with Arbitrary Sampling","created":"2018-09-11","cited_by_count":14},{"id":"1909.05350","title":"The Error-Feedback Framework: Better Rates for SGD with Delayed Gradients and Compressed Communication","created":"2019-09-11","cited_by_count":14},{"id":"2004.08657","title":"On Tight Convergence Rates of Without-replacement SGD","created":"2020-04-18","cited_by_count":3}],"next_cursor":null}