{"list":"other","total":81,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"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":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"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":"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":"1712.01887","title":"Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training","created":"2017-12-05","cited_by_count":478},{"id":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","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":"1901.09847","title":"Error Feedback Fixes SignSGD and other Gradient Compression Schemes","created":"2019-01-28","cited_by_count":310},{"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":"1902.00340","title":"Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication","created":"2019-02-01","cited_by_count":221},{"id":"1901.09401","title":"SGD: General Analysis and Improved Rates","created":"2019-01-27","cited_by_count":207},{"id":"1812.02903","title":"Applied Federated Learning: Improving Google Keyboard Query Suggestions","created":"2018-12-07","cited_by_count":204},{"id":"1808.07217","title":"Don't Use Large Mini-Batches, Use Local SGD","created":"2018-08-22","cited_by_count":202},{"id":"1912.09789","title":"A Survey on Distributed Machine Learning","created":"2019-12-20","cited_by_count":188},{"id":"1906.02367","title":"Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computations","created":"2019-06-06","cited_by_count":181},{"id":"1910.00962","title":"Privacy-preserving Federated Brain Tumour Segmentation","created":"2019-10-02","cited_by_count":169},{"id":"2007.01154","title":"Federated Learning with Compression: Unified Analysis and Sharp Guarantees","created":"2020-07-02","cited_by_count":160},{"id":"1310.7063","title":"On the Convergence of Decentralized Gradient Descent","created":"2013-10-26","cited_by_count":159},{"id":"1710.06952","title":"Asynchronous Decentralized Parallel Stochastic Gradient Descent","created":"2017-10-18","cited_by_count":159},{"id":"1811.10792","title":"Stochastic Gradient Push for Distributed Deep Learning","created":"2018-11-27","cited_by_count":152},{"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":"2002.12410","title":"On Biased Compression for Distributed Learning","created":"2020-02-27","cited_by_count":140},{"id":"1611.00429","title":"Distributed Mean Estimation with Limited Communication","created":"2016-11-02","cited_by_count":136},{"id":"1709.08765","title":"Network Topology and Communication-Computation Tradeoffs in Decentralized Optimization","created":"2017-09-26","cited_by_count":122},{"id":"1910.01500","title":"MLPerf Training Benchmark","created":"2019-10-02","cited_by_count":115},{"id":"1907.09356","title":"Decentralized Deep Learning with Arbitrary Communication Compression","created":"2019-07-22","cited_by_count":111},{"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":"2011.02828","title":"Local SGD: Unified Theory and New Efficient Methods","created":"2020-11-03","cited_by_count":88},{"id":"2006.08950","title":"Federated Accelerated Stochastic Gradient Descent","created":"2020-06-16","cited_by_count":85},{"id":"1702.08704","title":"Optimal algorithms for smooth and strongly convex distributed optimization in networks","created":"2017-02-28","cited_by_count":83},{"id":"1303.2289","title":"Distributed optimization over time-varying directed graphs","created":"2013-03-10","cited_by_count":78},{"id":"2102.07845","title":"MARINA: Faster Non-Convex Distributed Learning with Compression","created":"2021-02-15","cited_by_count":78},{"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":"1506.01900","title":"Communication Complexity of Distributed Convex Learning and Optimization","created":"2015-06-05","cited_by_count":60},{"id":"2011.08474","title":"Federated Composite Optimization","created":"2020-11-17","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":"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":"2002.04013","title":"Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts","created":"2020-02-10","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":"1806.00291","title":"Optimal Algorithms for Non-Smooth Distributed Optimization in Networks","created":"2018-06-01","cited_by_count":41},{"id":"2006.13838","title":"Advances in Asynchronous Parallel and Distributed Optimization","created":"2020-06-24","cited_by_count":40},{"id":"1505.04824","title":"An Asynchronous Mini-Batch Algorithm for Regularized Stochastic Optimization","created":"2015-05-18","cited_by_count":38},{"id":"1806.11536","title":"An Exact Quantized Decentralized Gradient Descent Algorithm","created":"2018-06-29","cited_by_count":36},{"id":"1406.2075","title":"Stochastic Gradient-Push for Strongly Convex Functions on Time-Varying Directed Graphs","created":"2014-06-09","cited_by_count":32},{"id":"2006.07013","title":"A Unified Analysis of Stochastic Gradient Methods for Nonconvex Federated Optimization","created":"2020-06-12","cited_by_count":28},{"id":"1809.00710","title":"A Dual Approach for Optimal Algorithms in Distributed Optimization over Networks","created":"2018-09-03","cited_by_count":27},{"id":"1910.09126","title":"Communication-Efficient Local Decentralized SGD Methods","created":"2019-10-21","cited_by_count":23},{"id":"1506.02396","title":"ARock: an Algorithmic Framework for Asynchronous Parallel Coordinate Updates","created":"2015-06-08","cited_by_count":21},{"id":"1905.03960","title":"Priority-based Parameter Propagation for Distributed DNN Training","created":"2019-05-10","cited_by_count":21},{"id":"1606.04809","title":"ASAGA: Asynchronous Parallel SAGA","created":"2016-06-15","cited_by_count":18},{"id":"1908.06077","title":"NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization","created":"2019-08-16","cited_by_count":18},{"id":"1909.02061","title":"Performance Analysis and Comparison of Distributed Machine Learning Systems","created":"2019-09-04","cited_by_count":9},{"id":"1910.08701","title":"Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks","created":"2019-10-19","cited_by_count":9},{"id":"2008.00177","title":"Multi-node Bert-pretraining: Cost-efficient Approach","created":"2020-08-01","cited_by_count":5},{"id":"1911.08527","title":"Projected Gradient Method for Decentralized Optimization over Time-Varying Networks","created":"2019-11-19","cited_by_count":1}],"next_cursor":null}