{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"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":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"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":"1904.01681","title":"Augmented Neural ODEs","created":"2019-04-02","cited_by_count":397},{"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":"1802.05799","title":"Horovod: fast and easy distributed deep learning in TensorFlow","created":"2018-02-15","cited_by_count":279},{"id":"2003.04887","title":"ReZero is All You Need: Fast Convergence at Large Depth","created":"2020-03-10","cited_by_count":264},{"id":"1704.05021","title":"Sparse Communication for Distributed Gradient Descent","created":"2017-04-17","cited_by_count":249},{"id":"1902.00340","title":"Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication","created":"2019-02-01","cited_by_count":221},{"id":"1710.10121","title":"Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations","created":"2017-10-27","cited_by_count":203},{"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":"1802.09941","title":"Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis","created":"2018-02-26","cited_by_count":156},{"id":"1610.02132","title":"QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding","created":"2016-10-07","cited_by_count":147},{"id":"1906.02762","title":"Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View","created":"2019-06-06","cited_by_count":113},{"id":"1412.6651","title":"Deep learning with Elastic Averaging SGD","created":"2014-12-20","cited_by_count":90},{"id":"1803.06443","title":"Communication Compression for Decentralized Training","created":"2018-03-17","cited_by_count":88},{"id":"1807.11205","title":"Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes","created":"2018-07-30","cited_by_count":63},{"id":"2003.05508","title":"A Mean-field Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth","created":"2020-03-11","cited_by_count":56},{"id":"2006.13838","title":"Advances in Asynchronous Parallel and Distributed Optimization","created":"2020-06-24","cited_by_count":40},{"id":"2011.04050","title":"Adaptive Federated Dropout: Improving Communication Efficiency and Generalization for Federated Learning","created":"2020-11-08","cited_by_count":38},{"id":"1812.04352","title":"Layer-Parallel Training of Deep Residual Neural Networks","created":"2018-12-11","cited_by_count":35},{"id":"1606.07365","title":"Parallel SGD: When does averaging help?","created":"2016-06-23","cited_by_count":32},{"id":"1809.02839","title":"Efficient and Robust Parallel DNN Training through Model Parallelism on Multi-GPU Platform","created":"2018-09-08","cited_by_count":28},{"id":"1711.04325","title":"Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes","created":"2017-11-12","cited_by_count":22},{"id":"1803.03383","title":"High-Accuracy Low-Precision Training","created":"2018-03-09","cited_by_count":20},{"id":"1803.08950","title":"Asynchronous Gradient-Push","created":"2018-03-23","cited_by_count":20},{"id":"1911.04610","title":"XPipe: Efficient Pipeline Model Parallelism for Multi-GPU DNN Training","created":"2019-10-24","cited_by_count":20},{"id":"1805.10111","title":"Double Quantization for Communication-Efficient Distributed Optimization","created":"2018-05-25","cited_by_count":19},{"id":"1712.04432","title":"Integrated Model, Batch and Domain Parallelism in Training Neural Networks","created":"2017-12-12","cited_by_count":16},{"id":"2007.05105","title":"AdaScale SGD: A User-Friendly Algorithm for Distributed Training","created":"2020-07-09","cited_by_count":16},{"id":"1711.05979","title":"Performance Modeling and Evaluation of Distributed Deep Learning Frameworks on GPUs","created":"2017-11-16","cited_by_count":13},{"id":"1901.08924","title":"Exploring Fast and Communication-Efficient Algorithms in Large-scale Distributed Networks","created":"2019-01-25","cited_by_count":8},{"id":"2006.12575","title":"LAMP: Large Deep Nets with Automated Model Parallelism for Image Segmentation","created":"2020-06-22","cited_by_count":8},{"id":"2007.07336","title":"Layer-Parallel Training with GPU Concurrency of Deep Residual Neural Networks via Nonlinear Multigrid","created":"2020-07-14","cited_by_count":8},{"id":"1906.05936","title":"Layered SGD: A Decentralized and Synchronous SGD Algorithm for Scalable Deep Neural Network Training","created":"2019-06-13","cited_by_count":2},{"id":"1906.08168","title":"Automatic Model Parallelism for Deep Neural Networks with Compiler and Hardware Support","created":"2019-06-11","cited_by_count":2}],"next_cursor":null}