{"list":"other","total":65,"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":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"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":"1806.00582","title":"Federated Learning with Non-IID Data","created":"2018-06-02","cited_by_count":1108},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"2007.07481","title":"Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization","created":"2020-07-15","cited_by_count":906},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"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":"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":"2010.01264","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","created":"2020-10-03","cited_by_count":337},{"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":"1703.00102","title":"SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient","created":"2017-03-01","cited_by_count":220},{"id":"2103.04628","title":"Personalized Federated Learning using Hypernetworks","created":"2021-03-08","cited_by_count":212},{"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":"1811.03600","title":"Measuring the Effects of Data Parallelism on Neural Network Training","created":"2018-11-08","cited_by_count":193},{"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":"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":"2007.07682","title":"FetchSGD: Communication-Efficient Federated Learning with Sketching","created":"2020-07-15","cited_by_count":179},{"id":"2002.03329","title":"Better Theory for SGD in the Nonconvex World","created":"2020-02-09","cited_by_count":158},{"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":"2006.04735","title":"Minibatch vs Local SGD for Heterogeneous Distributed Learning","created":"2020-06-08","cited_by_count":147},{"id":"1603.06160","title":"Stochastic Variance Reduction for Nonconvex Optimization","created":"2016-03-19","cited_by_count":145},{"id":"1308.6594","title":"Mini-batch Stochastic Approximation Methods for Nonconvex Stochastic Composite Optimization","created":"2013-08-29","cited_by_count":143},{"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":"2111.02862","title":"Parameterized Knowledge Transfer for Personalized Federated Learning","created":"2021-11-04","cited_by_count":109},{"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":"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":"2102.07845","title":"MARINA: Faster Non-Convex Distributed Learning with Compression","created":"2021-02-15","cited_by_count":78},{"id":"2004.01442","title":"From Local SGD to Local Fixed-Point Methods for Federated Learning","created":"2020-04-03","cited_by_count":74},{"id":"1603.05643","title":"Variance Reduction for Faster Non-Convex Optimization","created":"2016-03-17","cited_by_count":72},{"id":"2106.04159","title":"Fast Federated Learning in the Presence of Arbitrary Device Unavailability","created":"2021-06-08","cited_by_count":72},{"id":"2006.06954","title":"Towards Flexible Device Participation in Federated Learning","created":"2020-06-12","cited_by_count":65},{"id":"1605.07147","title":"Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds","created":"2016-05-23","cited_by_count":64},{"id":"1806.07811","title":"Stochastic Nested Variance Reduction for Nonconvex Optimization","created":"2018-06-20","cited_by_count":63},{"id":"1706.09156","title":"Non-convex Finite-Sum Optimization Via SCSG Methods","created":"2017-06-28","cited_by_count":61},{"id":"2006.14591","title":"Bidirectional compression in heterogeneous settings for distributed or federated learning with partial participation: tight convergence guarantees","created":"2020-06-25","cited_by_count":46},{"id":"1904.10120","title":"Semi-Cyclic Stochastic Gradient Descent","created":"2019-04-23","cited_by_count":40},{"id":"2103.03228","title":"One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning","created":"2021-03-04","cited_by_count":39},{"id":"2110.10342","title":"Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond","created":"2021-10-20","cited_by_count":36},{"id":"1507.02000","title":"An optimal randomized incremental gradient method","created":"2015-07-08","cited_by_count":33},{"id":"2102.03198","title":"Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning","created":"2021-02-05","cited_by_count":31},{"id":"1904.09265","title":"SSRGD: Simple Stochastic Recursive Gradient Descent for Escaping Saddle Points","created":"2019-04-19","cited_by_count":25},{"id":"2102.04635","title":"Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity","created":"2021-02-09","cited_by_count":21},{"id":"2002.07399","title":"Distributed Non-Convex Optimization with Sublinear Speedup under Intermittent Client Availability","created":"2020-02-18","cited_by_count":20},{"id":"2108.04755","title":"FedPAGE: A Fast Local Stochastic Gradient Method for Communication-Efficient Federated Learning","created":"2021-08-10","cited_by_count":20},{"id":"2002.05359","title":"Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization","created":"2020-02-13","cited_by_count":16},{"id":"2202.01268","title":"DASHA: Distributed Nonconvex Optimization with Communication Compression, Optimal Oracle Complexity, and No Client Synchronization","created":"2022-02-02","cited_by_count":16},{"id":"1610.04674","title":"Finite-sum Composition Optimization via Variance Reduced Gradient Descent","created":"2016-10-15","cited_by_count":15},{"id":"2110.03681","title":"Neural Tangent Kernel Empowered Federated Learning","created":"2021-10-07","cited_by_count":15},{"id":"1711.05762","title":"Random gradient extrapolation for distributed and stochastic optimization","created":"2017-11-15","cited_by_count":14},{"id":"1809.04146","title":"Nonconvex Variance Reduced Optimization with Arbitrary Sampling","created":"2018-09-11","cited_by_count":14},{"id":"1810.10690","title":"SpiderBoost and Momentum: Faster Stochastic Variance Reduction Algorithms","created":"2018-10-25","cited_by_count":11},{"id":"1610.00970","title":"Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum Structure","created":"2016-10-04","cited_by_count":8},{"id":"2112.09355","title":"From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimization","created":"2021-12-17","cited_by_count":8},{"id":"1709.08728","title":"Stochastic Nonconvex Optimization with Large Minibatches","created":"2017-09-25","cited_by_count":7},{"id":"1603.01860","title":"Generalization error bounds for learning to rank: Does the length of document lists matter?","created":"2016-03-06","cited_by_count":4}],"next_cursor":null}