{"list":"other","total":65,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"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":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"1603.04467","title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","created":"2016-03-14","cited_by_count":664},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"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":"1903.02891","title":"Robust and Communication-Efficient Federated Learning from Non-IID Data","created":"2019-03-07","cited_by_count":419},{"id":"1905.05583","title":"How to Fine-Tune BERT for Text Classification?","created":"2019-05-14","cited_by_count":411},{"id":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"id":"1711.00489","title":"Don't Decay the Learning Rate, Increase the Batch Size","created":"2017-11-01","cited_by_count":320},{"id":"1901.09847","title":"Error Feedback Fixes SignSGD and other Gradient Compression Schemes","created":"2019-01-28","cited_by_count":310},{"id":"1802.05799","title":"Horovod: fast and easy distributed deep learning in TensorFlow","created":"2018-02-15","cited_by_count":279},{"id":"1705.07878","title":"TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning","created":"2017-05-22","cited_by_count":256},{"id":"1704.05021","title":"Sparse Communication for Distributed Gradient Descent","created":"2017-04-17","cited_by_count":249},{"id":"1905.13727","title":"PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization","created":"2019-05-31","cited_by_count":238},{"id":"1809.10505","title":"The Convergence of Sparsified Gradient Methods","created":"2018-09-27","cited_by_count":229},{"id":"1902.00340","title":"Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication","created":"2019-02-01","cited_by_count":221},{"id":"1710.09854","title":"Gradient Sparsification for Communication-Efficient Distributed Optimization","created":"2017-10-26","cited_by_count":201},{"id":"1807.05358","title":"Beyond Data and Model Parallelism for Deep Neural Networks","created":"2018-07-14","cited_by_count":179},{"id":"1803.07068","title":"D$^2$: Decentralized Training over Decentralized Data","created":"2018-03-19","cited_by_count":140},{"id":"1611.00429","title":"Distributed Mean Estimation with Limited Communication","created":"2016-11-02","cited_by_count":136},{"id":"1806.04090","title":"ATOMO: Communication-efficient Learning via Atomic Sparsification","created":"2018-06-11","cited_by_count":136},{"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":"1905.05957","title":"DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression","created":"2019-05-15","cited_by_count":99},{"id":"1905.10988","title":"Natural Compression for Distributed Deep Learning","created":"2019-05-27","cited_by_count":90},{"id":"1803.06443","title":"Communication Compression for Decentralized Training","created":"2018-03-17","cited_by_count":88},{"id":"1802.08241","title":"Hessian-based Analysis of Large Batch Training and Robustness to Adversaries","created":"2018-02-22","cited_by_count":87},{"id":"1908.00080","title":"Machine Learning at the Network Edge: A Survey","created":"2019-07-31","cited_by_count":84},{"id":"1903.04488","title":"Communication-efficient distributed SGD with Sketching","created":"2019-03-12","cited_by_count":81},{"id":"1806.08054","title":"Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization","created":"2018-06-21","cited_by_count":76},{"id":"1903.06701","title":"Scaling Distributed Machine Learning with In-Network Aggregation","created":"2019-02-22","cited_by_count":65},{"id":"1511.04561","title":"8-Bit Approximations for Parallelism in Deep Learning","created":"2015-11-14","cited_by_count":56},{"id":"1911.08772","title":"Understanding Top-k Sparsification in Distributed Deep Learning","created":"2019-11-20","cited_by_count":56},{"id":"1805.08768","title":"Sparse Binary Compression: Towards Distributed Deep Learning with minimal Communication","created":"2018-05-22","cited_by_count":51},{"id":"1905.10936","title":"Communication-Efficient Distributed Blockwise Momentum SGD with Error-Feedback","created":"2019-05-27","cited_by_count":50},{"id":"1901.04359","title":"A Distributed Synchronous SGD Algorithm with Global Top-$k$ Sparsification for Low Bandwidth Networks","created":"2019-01-14","cited_by_count":37},{"id":"2101.10761","title":"An Efficient Statistical-based Gradient Compression Technique for Distributed Training Systems","created":"2021-01-26","cited_by_count":32},{"id":"1712.02029","title":"AdaBatch: Adaptive Batch Sizes for Training Deep Neural Networks","created":"2017-12-06","cited_by_count":29},{"id":"1803.03288","title":"TicTac: Accelerating Distributed Deep Learning with Communication Scheduling","created":"2018-03-08","cited_by_count":27},{"id":"2004.08488","title":"Network-Aware Optimization of Distributed Learning for Fog Computing","created":"2020-04-17","cited_by_count":27},{"id":"2003.06307","title":"Communication-Efficient Distributed Deep Learning: A Comprehensive Survey","created":"2020-03-10","cited_by_count":26},{"id":"1511.00175","title":"FireCaffe: near-linear acceleration of deep neural network training on compute clusters","created":"2015-10-31","cited_by_count":25},{"id":"1802.04924","title":"Exploring Hidden Dimensions in Parallelizing Convolutional Neural Networks","created":"2018-02-14","cited_by_count":23},{"id":"2010.10458","title":"Towards Scalable Distributed Training of Deep Learning on Public Cloud Clusters","created":"2020-10-20","cited_by_count":23},{"id":"1802.06058","title":"Variance-based Gradient Compression for Efficient Distributed Deep Learning","created":"2018-02-16","cited_by_count":22},{"id":"2006.03318","title":"Daydream: Accurately Estimating the Efficacy of Optimizations for DNN Training","created":"2020-06-05","cited_by_count":22},{"id":"1806.01427","title":"Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmark","created":"2018-06-04","cited_by_count":21},{"id":"1811.03617","title":"GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training","created":"2018-11-08","cited_by_count":21},{"id":"2006.10103","title":"Is Network the Bottleneck of Distributed Training?","created":"2020-06-17","cited_by_count":20},{"id":"1810.01021","title":"Large batch size training of neural networks with adversarial training and second-order information","created":"2018-10-02","cited_by_count":18},{"id":"1902.11259","title":"Distributed Learning with Sublinear Communication","created":"2019-02-28","cited_by_count":9},{"id":"1901.08924","title":"Exploring Fast and Communication-Efficient Algorithms in Large-scale Distributed Networks","created":"2019-01-25","cited_by_count":8},{"id":"1803.06905","title":"TBD: Benchmarking and Analyzing Deep Neural Network Training","created":"2018-03-16","cited_by_count":6},{"id":"1812.03871","title":"Distributed Learning with Sparse Communications by Identification","created":"2018-12-10","cited_by_count":1}],"next_cursor":null}