{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"1905.12616","title":"Defending Against Neural Fake News","created":"2019-05-29","cited_by_count":559},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"1705.09056","title":"Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent","created":"2017-05-25","cited_by_count":502},{"id":"1901.09847","title":"Error Feedback Fixes SignSGD and other Gradient Compression Schemes","created":"2019-01-28","cited_by_count":310},{"id":"2010.07468","title":"AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients","created":"2020-10-15","cited_by_count":283},{"id":"1705.07878","title":"TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning","created":"2017-05-22","cited_by_count":256},{"id":"1806.02847","title":"A Simple Method for Commonsense Reasoning","created":"2018-06-07","cited_by_count":223},{"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":"1902.09843","title":"Adaptive Gradient Methods with Dynamic Bound of Learning Rate","created":"2019-02-26","cited_by_count":183},{"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":"1808.02941","title":"On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization","created":"2018-08-08","cited_by_count":174},{"id":"2003.02395","title":"A Simple Convergence Proof of Adam and Adagrad","created":"2020-03-05","cited_by_count":171},{"id":"1705.07774","title":"Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients","created":"2017-05-22","cited_by_count":139},{"id":"1806.04090","title":"ATOMO: Communication-efficient Learning via Atomic Sparsification","created":"2018-06-11","cited_by_count":136},{"id":"1811.09358","title":"A Sufficient Condition for Convergences of Adam and RMSProp","created":"2018-11-23","cited_by_count":126},{"id":"1506.08272","title":"Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization","created":"2015-06-27","cited_by_count":116},{"id":"1907.09356","title":"Decentralized Deep Learning with Arbitrary Communication Compression","created":"2019-07-22","cited_by_count":111},{"id":"1905.05957","title":"DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression","created":"2019-05-15","cited_by_count":99},{"id":"1808.05671","title":"On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization","created":"2018-08-16","cited_by_count":91},{"id":"1910.06513","title":"ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization","created":"2019-10-15","cited_by_count":76},{"id":"2102.02888","title":"1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed","created":"2021-02-04","cited_by_count":75},{"id":"2006.08085","title":"Optimal Complexity in Decentralized Training","created":"2020-06-15","cited_by_count":60},{"id":"1903.07020","title":"Zeno++: Robust Fully Asynchronous SGD","created":"2019-03-17","cited_by_count":53},{"id":"1905.12938","title":"Stochastic Sign Descent Methods: New Algorithms and Better Theory","created":"2019-05-30","cited_by_count":49},{"id":"2002.10940","title":"Stochastic-Sign SGD for Federated Learning with Theoretical Guarantees","created":"2020-02-25","cited_by_count":35},{"id":"2003.09729","title":"A new regret analysis for Adam-type algorithms","created":"2020-03-21","cited_by_count":35},{"id":"2012.06188","title":"Recent Theoretical Advances in Non-Convex Optimization","created":"2020-12-11","cited_by_count":30},{"id":"1906.01736","title":"Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms","created":"2019-06-04","cited_by_count":29},{"id":"1810.00143","title":"AdaShift: Decorrelation and Convergence of Adaptive Learning Rate Methods","created":"2018-09-29","cited_by_count":24},{"id":"2002.11787","title":"Moniqua: Modulo Quantized Communication in Decentralized SGD","created":"2020-02-26","cited_by_count":24},{"id":"2104.06069","title":"1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed","created":"2021-04-13","cited_by_count":24},{"id":"1910.06093","title":"Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks","created":"2019-10-14","cited_by_count":20},{"id":"2109.03194","title":"On the Convergence of Decentralized Adaptive Gradient Methods","created":"2021-09-07","cited_by_count":17},{"id":"1805.07557","title":"Nostalgic Adam: Weighting more of the past gradients when designing the adaptive learning rate","created":"2018-05-19","cited_by_count":16},{"id":"2109.07497","title":"Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD","created":"2021-09-15","cited_by_count":14},{"id":"2105.04808","title":"DP-SIGNSGD: When Efficiency Meets Privacy and Robustness","created":"2021-05-11","cited_by_count":11},{"id":"2110.02998","title":"Federated Learning via Plurality Vote","created":"2021-10-06","cited_by_count":6},{"id":"1905.09356","title":"Convergence Analyses of Online ADAM Algorithm in Convex Setting and Two-Layer ReLU Neural Network","created":"2019-05-22","cited_by_count":4},{"id":"1807.08023","title":"signProx: One-Bit Proximal Algorithm for Nonconvex Stochastic Optimization","created":"2018-07-20","cited_by_count":2},{"id":"2005.06706","title":"MixML: A Unified Analysis of Weakly Consistent Parallel Learning","created":"2020-05-14","cited_by_count":2}],"next_cursor":null}