{"list":"other","total":187,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"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":"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":"1909.04746","title":"Tighter Theory for Local SGD on Identical and Heterogeneous Data","created":"2019-09-10","cited_by_count":266},{"id":"1909.12326","title":"Model Pruning Enables Efficient Federated Learning on Edge Devices","created":"2019-09-26","cited_by_count":222},{"id":"2002.05516","title":"Federated Learning of a Mixture of Global and Local Models","created":"2020-02-10","cited_by_count":210},{"id":"1901.09401","title":"SGD: General Analysis and Improved Rates","created":"2019-01-27","cited_by_count":207},{"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":"1812.07210","title":"Expanding the Reach of Federated Learning by Reducing Client Resource Requirements","created":"2018-12-18","cited_by_count":163},{"id":"2002.03329","title":"Better Theory for SGD in the Nonconvex World","created":"2020-02-09","cited_by_count":158},{"id":"2002.12410","title":"On Biased Compression for Distributed Learning","created":"2020-02-27","cited_by_count":140},{"id":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134},{"id":"2106.05203","title":"EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback","created":"2021-06-09","cited_by_count":133},{"id":"2006.07253","title":"Dynamic Model Pruning with Feedback","created":"2020-06-12","cited_by_count":125},{"id":"2010.13723","title":"Optimal Client Sampling for Federated Learning","created":"2020-10-26","cited_by_count":124},{"id":"2008.10898","title":"PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization","created":"2020-08-25","cited_by_count":119},{"id":"1907.04164","title":"Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model","created":"2019-07-09","cited_by_count":117},{"id":"1901.09269","title":"Distributed Learning with Compressed Gradient Differences","created":"2019-01-26","cited_by_count":112},{"id":"2212.01548","title":"FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction","created":"2022-12-03","cited_by_count":102},{"id":"1802.03801","title":"SGD and Hogwild! Convergence Without the Bounded Gradients Assumption","created":"2018-02-11","cited_by_count":95},{"id":"1905.10988","title":"Natural Compression for Distributed Deep Learning","created":"2019-05-27","cited_by_count":90},{"id":"2002.11364","title":"Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization","created":"2020-02-26","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":"2008.00051","title":"On the Convergence of SGD with Biased Gradients","created":"2020-07-31","cited_by_count":83},{"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":"2010.00892","title":"Variance-Reduced Methods for Machine Learning","created":"2020-10-02","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":"2004.01442","title":"From Local SGD to Local Fixed-Point Methods for Federated Learning","created":"2020-04-03","cited_by_count":74},{"id":"1901.08689","title":"Don't Jump Through Hoops and Remove Those Loops: SVRG and Katyusha are Better Without the Outer Loop","created":"2019-01-24","cited_by_count":68},{"id":"1903.06701","title":"Scaling Distributed Machine Learning with In-Network Aggregation","created":"2019-02-22","cited_by_count":65},{"id":"2302.00999","title":"High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance","created":"2023-02-02","cited_by_count":61},{"id":"2109.15258","title":"Federated Dropout -- A Simple Approach for Enabling Federated Learning on Resource Constrained Devices","created":"2021-09-30","cited_by_count":56},{"id":"1806.06573","title":"Distributed learning with compressed gradients","created":"2018-06-18","cited_by_count":55},{"id":"2106.02969","title":"FedNL: Making Newton-Type Methods Applicable to Federated Learning","created":"2021-06-05","cited_by_count":52},{"id":"1712.09677","title":"Momentum and Stochastic Momentum for Stochastic Gradient, Newton, Proximal Point and Subspace Descent Methods","created":"2017-12-27","cited_by_count":49},{"id":"1905.12938","title":"Stochastic Sign Descent Methods: New Algorithms and Better Theory","created":"2019-05-30","cited_by_count":49},{"id":"1806.10188","title":"A Tight Convergence Analysis for Stochastic Gradient Descent with Delayed Updates","created":"2018-06-26","cited_by_count":47},{"id":"2002.08958","title":"Uncertainty Principle for Communication Compression in Distributed and Federated Learning and the Search for an Optimal Compressor","created":"2020-02-20","cited_by_count":45},{"id":"2010.00091","title":"Error Compensated Distributed SGD Can Be Accelerated","created":"2020-09-30","cited_by_count":45},{"id":"2208.02507","title":"ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity","created":"2022-08-04","cited_by_count":45},{"id":"2006.11077","title":"A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning","created":"2020-06-19","cited_by_count":43},{"id":"2006.11773","title":"Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization","created":"2020-06-21","cited_by_count":43},{"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":"1611.07555","title":"Randomized Distributed Mean Estimation: Accuracy vs Communication","created":"2016-11-22","cited_by_count":39},{"id":"2010.03246","title":"Optimal Gradient Compression for Distributed and Federated Learning","created":"2020-10-07","cited_by_count":39},{"id":"1602.02283","title":"Importance Sampling for Minibatches","created":"2016-02-06","cited_by_count":36},{"id":"2006.11573","title":"Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization","created":"2020-06-20","cited_by_count":36},{"id":"2006.09270","title":"Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithm","created":"2020-06-16","cited_by_count":35},{"id":"1805.02632","title":"Stochastic Quasi-Gradient Methods: Variance Reduction via Jacobian Sketching","created":"2018-05-07","cited_by_count":34},{"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":"2305.15155","title":"Momentum Provably Improves Error Feedback!","created":"2023-05-24","cited_by_count":31},{"id":"1811.12403","title":"New Convergence Aspects of Stochastic Gradient Algorithms","created":"2018-11-10","cited_by_count":30},{"id":"1706.04957","title":"Stochastic Primal-Dual Hybrid Gradient Algorithm with Arbitrary Sampling and Imaging Applications","created":"2017-06-15","cited_by_count":29},{"id":"2006.07013","title":"A Unified Analysis of Stochastic Gradient Methods for Nonconvex Federated Optimization","created":"2020-06-12","cited_by_count":28},{"id":"2207.12891","title":"RandProx: Primal-Dual Optimization Algorithms with Randomized Proximal Updates","created":"2022-07-26","cited_by_count":28},{"id":"2209.15218","title":"EF21-P and Friends: Improved Theoretical Communication Complexity for Distributed Optimization with Bidirectional Compression","created":"2022-09-30","cited_by_count":28},{"id":"2202.00998","title":"3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation","created":"2022-02-02","cited_by_count":27},{"id":"2102.07158","title":"Distributed Second Order Methods with Fast Rates and Compressed Communication","created":"2021-02-14","cited_by_count":25},{"id":"1603.09649","title":"Stochastic Block BFGS: Squeezing More Curvature out of Data","created":"2016-03-31","cited_by_count":24},{"id":"1902.03591","title":"Stochastic Three Points Method for Unconstrained Smooth Minimization","created":"2019-02-10","cited_by_count":24},{"id":"1912.01597","title":"Stochastic Newton and Cubic Newton Methods with Simple Local Linear-Quadratic Rates","created":"2019-12-03","cited_by_count":24},{"id":"2305.12387","title":"Optimal Time Complexities of Parallel Stochastic Optimization Methods Under a Fixed Computation Model","created":"2023-05-21","cited_by_count":24},{"id":"1310.2059","title":"Distributed Coordinate Descent Method for Learning with Big Data","created":"2013-10-08","cited_by_count":23},{"id":"1512.04039","title":"Distributed Optimization with Arbitrary Local Solvers","created":"2015-12-13","cited_by_count":23},{"id":"1512.09103","title":"Even Faster Accelerated Coordinate Descent Using Non-Uniform Sampling","created":"2015-12-30","cited_by_count":23},{"id":"2107.09461","title":"CANITA: Faster Rates for Distributed Convex Optimization with Communication Compression","created":"2021-07-20","cited_by_count":23},{"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":"2002.09526","title":"Stochastic Subspace Cubic Newton Method","created":"2020-02-21","cited_by_count":21},{"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":"2106.03076","title":"A Convergence Theory for SVGD in the Population Limit under Talagrand's Inequality T1","created":"2021-06-06","cited_by_count":21},{"id":"2204.13169","title":"FedShuffle: Recipes for Better Use of Local Work in Federated Learning","created":"2022-04-27","cited_by_count":21},{"id":"1808.03045","title":"Accelerated Bregman Proximal Gradient Methods for Relatively Smooth Convex Optimization","created":"2018-08-09","cited_by_count":20},{"id":"1910.02120","title":"Distributed Learning of Deep Neural Networks using Independent Subnet Training","created":"2019-10-04","cited_by_count":20},{"id":"1502.03508","title":"Adding vs. Averaging in Distributed Primal-Dual Optimization","created":"2015-02-12","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":"2106.04469","title":"Lower Bounds and Optimal Algorithms for Smooth and Strongly Convex Decentralized Optimization Over Time-Varying Networks","created":"2021-06-08","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":"2107.00961","title":"ResIST: Layer-Wise Decomposition of ResNets for Distributed Training","created":"2021-07-02","cited_by_count":18},{"id":"2206.07021","title":"Federated Optimization Algorithms with Random Reshuffling and Gradient Compression","created":"2022-06-14","cited_by_count":18},{"id":"1905.11768","title":"Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates","created":"2019-05-28","cited_by_count":17},{"id":"2102.12810","title":"Hyperparameter Transfer Learning with Adaptive Complexity","created":"2021-02-25","cited_by_count":17},{"id":"2208.05174","title":"FedOBD: Opportunistic Block Dropout for Efficiently Training Large-scale Neural Networks through Federated Learning","created":"2022-08-10","cited_by_count":17},{"id":"1706.01108","title":"Stochastic Reformulations of Linear Systems: Algorithms and Convergence Theory","created":"2017-06-04","cited_by_count":16},{"id":"2002.05359","title":"Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization","created":"2020-02-13","cited_by_count":16},{"id":"2106.08895","title":"Masked Training of Neural Networks with Partial Gradients","created":"2021-06-16","cited_by_count":16},{"id":"2109.05198","title":"Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information","created":"2021-09-11","cited_by_count":16},{"id":"2112.15199","title":"Accelerated Primal-Dual Gradient Method for Smooth and Convex-Concave Saddle-Point Problems with Bilinear Coupling","created":"2021-12-30","cited_by_count":16},{"id":"2206.00508","title":"Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition","created":"2022-06-01","cited_by_count":16},{"id":"2211.00188","title":"Adaptive Compression for Communication-Efficient Distributed Training","created":"2022-10-31","cited_by_count":16},{"id":"2102.09700","title":"AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods","created":"2021-02-19","cited_by_count":15},{"id":"2110.03313","title":"Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees","created":"2021-10-07","cited_by_count":15},{"id":"2111.01847","title":"Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning","created":"2021-11-02","cited_by_count":15}],"next_cursor":"100"}