{"list":"other","total":68,"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":"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"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":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1312.4400","title":"Network In Network","created":"2013-12-16","cited_by_count":605},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"1606.06160","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","created":"2016-06-20","cited_by_count":569},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"1712.01887","title":"Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training","created":"2017-12-05","cited_by_count":478},{"id":"1707.06342","title":"ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression","created":"2017-07-20","cited_by_count":442},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"id":"1901.09847","title":"Error Feedback Fixes SignSGD and other Gradient Compression Schemes","created":"2019-01-28","cited_by_count":310},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"1405.3866","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","created":"2014-05-15","cited_by_count":284},{"id":"1608.05859","title":"Using the Output Embedding to Improve Language Models","created":"2016-08-20","cited_by_count":272},{"id":"1705.07878","title":"TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning","created":"2017-05-22","cited_by_count":256},{"id":"1605.00459","title":"Multi30K: Multilingual English-German Image Descriptions","created":"2016-05-02","cited_by_count":250},{"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":"1711.05908","title":"NISP: Pruning Networks using Neuron Importance Score Propagation","created":"2017-11-16","cited_by_count":228},{"id":"1607.03250","title":"Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures","created":"2016-07-12","cited_by_count":221},{"id":"1702.03044","title":"Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights","created":"2017-02-10","cited_by_count":217},{"id":"1512.06473","title":"Quantized Convolutional Neural Networks for Mobile Devices","created":"2015-12-21","cited_by_count":215},{"id":"1612.01064","title":"Trained Ternary Quantization","created":"2016-12-04","cited_by_count":208},{"id":"1909.11957","title":"Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks","created":"2019-09-26","cited_by_count":160},{"id":"2002.09572","title":"The Break-Even Point on Optimization Trajectories of Deep Neural Networks","created":"2020-02-21","cited_by_count":150},{"id":"1702.05800","title":"Revisiting Distributed Synchronous SGD","created":"2017-02-19","cited_by_count":142},{"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":"1611.05128","title":"Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning","created":"2016-11-16","cited_by_count":134},{"id":"1905.05957","title":"DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression","created":"2019-05-15","cited_by_count":99},{"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":"1507.06970","title":"Perturbed Iterate Analysis for Asynchronous Stochastic Optimization","created":"2015-07-24","cited_by_count":67},{"id":"1611.07555","title":"Randomized Distributed Mean Estimation: Accuracy vs Communication","created":"2016-11-22","cited_by_count":39},{"id":"1802.08021","title":"SparCML: High-Performance Sparse Communication for Machine Learning","created":"2018-02-22","cited_by_count":34},{"id":"1712.02679","title":"AdaComp : Adaptive Residual Gradient Compression for Data-Parallel Distributed Training","created":"2017-12-07","cited_by_count":33},{"id":"1506.06438","title":"Taming the Wild: A Unified Analysis of Hogwild!-Style Algorithms","created":"2015-06-22","cited_by_count":31},{"id":"2003.08237","title":"Fixing the train-test resolution discrepancy: FixEfficientNet","created":"2020-03-18","cited_by_count":31},{"id":"2002.10376","title":"The Two Regimes of Deep Network Training","created":"2020-02-24","cited_by_count":30},{"id":"1511.06744","title":"Training CNNs with Low-Rank Filters for Efficient Image Classification","created":"2015-11-20","cited_by_count":25},{"id":"1802.06058","title":"Variance-based Gradient Compression for Efficient Distributed Deep Learning","created":"2018-02-16","cited_by_count":22},{"id":"1803.03383","title":"High-Accuracy Low-Precision Training","created":"2018-03-09","cited_by_count":20},{"id":"2010.16248","title":"Accordion: Adaptive Gradient Communication via Critical Learning Regime Identification","created":"2020-10-29","cited_by_count":19},{"id":"1606.04809","title":"ASAGA: Asynchronous Parallel SAGA","created":"2016-06-15","cited_by_count":18},{"id":"2007.00811","title":"Go Wide, Then Narrow: Efficient Training of Deep Thin Networks","created":"2020-07-01","cited_by_count":12},{"id":"2006.13347","title":"Principal Component Networks: Parameter Reduction Early in Training","created":"2020-06-23","cited_by_count":9}],"next_cursor":null}