{"list":"other","total":79,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"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":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"1803.01498","title":"Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates","created":"2018-03-05","cited_by_count":711},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"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":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"id":"1802.07927","title":"The Hidden Vulnerability of Distributed Learning in Byzantium","created":"2018-02-22","cited_by_count":329},{"id":"1912.13445","title":"Robust Aggregation for Federated Learning","created":"2019-12-31","cited_by_count":317},{"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":"1902.06156","title":"A Little Is Enough: Circumventing Defenses For Distributed Learning","created":"2019-02-16","cited_by_count":288},{"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":"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":"2003.00307","title":"Loss landscapes and optimization in over-parameterized non-linear systems and neural networks","created":"2020-02-29","cited_by_count":233},{"id":"1902.00340","title":"Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication","created":"2019-02-01","cited_by_count":221},{"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":"1906.02367","title":"Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computations","created":"2019-06-06","cited_by_count":181},{"id":"2012.06337","title":"Privacy and Robustness in Federated Learning: Attacks and Defenses","created":"2020-12-07","cited_by_count":166},{"id":"1309.2388","title":"Minimizing Finite Sums with the Stochastic Average Gradient","created":"2013-09-10","cited_by_count":164},{"id":"2007.01154","title":"Federated Learning with Compression: Unified Analysis and Sharp Guarantees","created":"2020-07-02","cited_by_count":160},{"id":"1903.03936","title":"Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulation","created":"2019-03-10","cited_by_count":141},{"id":"2002.12410","title":"On Biased Compression for Distributed Learning","created":"2020-02-27","cited_by_count":140},{"id":"2012.10333","title":"Learning from History for Byzantine Robust Optimization","created":"2020-12-18","cited_by_count":137},{"id":"1611.00429","title":"Distributed Mean Estimation with Limited Communication","created":"2016-11-02","cited_by_count":136},{"id":"1603.05953","title":"Katyusha: The First Direct Acceleration of Stochastic Gradient Methods","created":"2016-03-18","cited_by_count":135},{"id":"2106.05203","title":"EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback","created":"2021-06-09","cited_by_count":133},{"id":"2006.09365","title":"Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing","created":"2020-06-16","cited_by_count":128},{"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":"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":"1803.08917","title":"Byzantine Stochastic Gradient Descent","created":"2018-03-23","cited_by_count":81},{"id":"1912.12716","title":"Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attacks","created":"2019-12-29","cited_by_count":79},{"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":"1803.09877","title":"DRACO: Byzantine-resilient Distributed Training via Redundant Gradients","created":"2018-03-27","cited_by_count":75},{"id":"1904.05115","title":"Stochastic Distributed Learning with Gradient Quantization and Variance Reduction","created":"2019-04-10","cited_by_count":65},{"id":"2010.12292","title":"Linearly Converging Error Compensated SGD","created":"2020-10-23","cited_by_count":61},{"id":"2106.10207","title":"Distributed Deep Learning in Open Collaborations","created":"2021-06-18","cited_by_count":58},{"id":"2012.14368","title":"Byzantine-Resilient Non-Convex Stochastic Gradient Descent","created":"2020-12-28","cited_by_count":57},{"id":"2008.00742","title":"Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)","created":"2020-08-03","cited_by_count":54},{"id":"2106.02969","title":"FedNL: Making Newton-Type Methods Applicable to Federated Learning","created":"2021-06-05","cited_by_count":52},{"id":"1908.08098","title":"BRIDGE: Byzantine-resilient Decentralized Gradient Descent","created":"2019-08-21","cited_by_count":45},{"id":"2010.00091","title":"Error Compensated Distributed SGD Can Be Accelerated","created":"2020-09-30","cited_by_count":45},{"id":"2010.12460","title":"Adaptive Gradient Quantization for Data-Parallel SGD","created":"2020-10-23","cited_by_count":45},{"id":"1907.12205","title":"DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation","created":"2019-07-29","cited_by_count":44},{"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":"2108.00951","title":"Rethinking gradient sparsification as total error minimization","created":"2021-08-02","cited_by_count":41},{"id":"2202.07262","title":"Stochastic Gradient Descent-Ascent: Unified Theory and New Efficient Methods","created":"2022-02-15","cited_by_count":37},{"id":"1708.08155","title":"ByRDiE: Byzantine-resilient distributed coordinate descent for decentralized learning","created":"2017-08-28","cited_by_count":36},{"id":"1507.02000","title":"An optimal randomized incremental gradient method","created":"2015-07-08","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":"2102.07158","title":"Distributed Second Order Methods with Fast Rates and Compressed Communication","created":"2021-02-14","cited_by_count":25},{"id":"1905.12412","title":"A unified variance-reduced accelerated gradient method for convex optimization","created":"2019-05-29","cited_by_count":24},{"id":"2107.09461","title":"CANITA: Faster Rates for Distributed Convex Optimization with Communication Compression","created":"2021-07-20","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":"2006.08737","title":"Distributed Newton Can Communicate Less and Resist Byzantine Workers","created":"2020-06-15","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":"1911.09721","title":"Communication-Efficient and Byzantine-Robust Distributed Learning with Error Feedback","created":"2019-11-21","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":"1310.3438","title":"On Optimal Probabilities in Stochastic Coordinate Descent Methods","created":"2013-10-13","cited_by_count":14},{"id":"1412.8060","title":"Coordinate Descent with Arbitrary Sampling I: Algorithms and Complexity","created":"2014-12-27","cited_by_count":14},{"id":"1809.04146","title":"Nonconvex Variance Reduced Optimization with Arbitrary Sampling","created":"2018-09-11","cited_by_count":14},{"id":"1906.01481","title":"L-SVRG and L-Katyusha with Arbitrary Sampling","created":"2019-06-04","cited_by_count":14},{"id":"2106.11257","title":"Secure Distributed Training at Scale","created":"2021-06-21","cited_by_count":12},{"id":"1901.08669","title":"SAGA with Arbitrary Sampling","created":"2019-01-24","cited_by_count":10},{"id":"1905.13278","title":"A Stochastic Derivative Free Optimization Method with Momentum","created":"2019-05-30","cited_by_count":9},{"id":"2101.12316","title":"Byzantine Fault-Tolerance in Peer-to-Peer Distributed Gradient-Descent","created":"2021-01-28","cited_by_count":6},{"id":"2203.02383","title":"Distributed Methods with Absolute Compression and Error Compensation","created":"2022-03-04","cited_by_count":4}],"next_cursor":null}