{"list":"other","total":61,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"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":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1707.06342","title":"ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression","created":"2017-07-20","cited_by_count":442},{"id":"1402.1869","title":"On the Number of Linear Regions of Deep Neural Networks","created":"2014-02-08","cited_by_count":381},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"1404.0736","title":"Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation","created":"2014-04-02","cited_by_count":306},{"id":"1606.05336","title":"On the Expressive Power of Deep Neural Networks","created":"2016-06-16","cited_by_count":306},{"id":"1405.3866","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","created":"2014-05-15","cited_by_count":284},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"1711.05908","title":"NISP: Pruning Networks using Neuron Importance Score Propagation","created":"2017-11-16","cited_by_count":228},{"id":"1306.0543","title":"Predicting Parameters in Deep Learning","created":"2013-06-03","cited_by_count":224},{"id":"1705.07565","title":"Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon","created":"2017-05-22","cited_by_count":221},{"id":"1903.06758","title":"Algorithms for Verifying Deep Neural Networks","created":"2019-03-15","cited_by_count":221},{"id":"1412.6553","title":"Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition","created":"2014-12-19","cited_by_count":203},{"id":"2002.08307","title":"Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning","created":"2020-02-19","cited_by_count":185},{"id":"2009.08576","title":"Pruning Neural Networks at Initialization: Why are We Missing the Mark?","created":"2020-09-18","cited_by_count":182},{"id":"1911.05248","title":"What Do Compressed Deep Neural Networks Forget?","created":"2019-11-13","cited_by_count":171},{"id":"1901.09021","title":"Complexity of Linear Regions in Deep Networks","created":"2019-01-25","cited_by_count":167},{"id":"2010.03058","title":"Characterising Bias in Compressed Models","created":"2020-10-06","cited_by_count":167},{"id":"1711.02114","title":"Bounding and Counting Linear Regions of Deep Neural Networks","created":"2017-11-06","cited_by_count":161},{"id":"1906.00904","title":"Deep ReLU Networks Have Surprisingly Few Activation Patterns","created":"2019-06-03","cited_by_count":161},{"id":"1804.05862","title":"Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach","created":"2018-04-16","cited_by_count":126},{"id":"1811.08359","title":"Strong mixed-integer programming formulations for trained neural networks","created":"2018-11-20","cited_by_count":115},{"id":"1507.06149","title":"Data-free parameter pruning for Deep Neural Networks","created":"2015-07-22","cited_by_count":112},{"id":"1905.05934","title":"EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis","created":"2019-05-15","cited_by_count":98},{"id":"1705.01040","title":"Maximum Resilience of Artificial Neural Networks","created":"2017-04-28","cited_by_count":97},{"id":"1906.06307","title":"A Signal Propagation Perspective for Pruning Neural Networks at Initialization","created":"2019-06-14","cited_by_count":96},{"id":"1312.6098","title":"On the number of response regions of deep feed forward networks with piece-wise linear activations","created":"2013-12-20","cited_by_count":94},{"id":"1910.00744","title":"Reverse-Engineering Deep ReLU Networks","created":"2019-10-02","cited_by_count":83},{"id":"1506.02515","title":"Fast ConvNets Using Group-wise Brain Damage","created":"2015-06-08","cited_by_count":82},{"id":"1709.06662","title":"Verifying Properties of Binarized Deep Neural Networks","created":"2017-09-19","cited_by_count":79},{"id":"1809.03008","title":"Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability","created":"2018-09-09","cited_by_count":67},{"id":"2010.12001","title":"Reinforcement Learning with Combinatorial Actions: An Application to Vehicle Routing","created":"2020-10-22","cited_by_count":61},{"id":"1802.09052","title":"Wide Compression: Tensor Ring Nets","created":"2018-02-25","cited_by_count":50},{"id":"1909.11274","title":"Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural network","created":"2019-09-25","cited_by_count":39},{"id":"2001.00218","title":"Lossless Compression of Deep Neural Networks","created":"2020-01-01","cited_by_count":34},{"id":"2006.10621","title":"On the Predictability of Pruning Across Scales","created":"2020-06-18","cited_by_count":33},{"id":"1911.09461","title":"JANOS: An Integrated Predictive and Prescriptive Modeling Framework","created":"2019-11-21","cited_by_count":27},{"id":"1511.05077","title":"Diversity Networks: Neural Network Compression Using Determinantal Point Processes","created":"2015-11-16","cited_by_count":25},{"id":"1810.03370","title":"Empirical Bounds on Linear Regions of Deep Rectifier Networks","created":"2018-10-08","cited_by_count":23},{"id":"2009.09936","title":"Prune Responsibly","created":"2020-09-10","cited_by_count":20},{"id":"1807.10585","title":"Filter Distillation for Network Compression","created":"2018-07-20","cited_by_count":17},{"id":"1905.09803","title":"How degenerate is the parametrization of neural networks with the ReLU activation function?","created":"2019-05-23","cited_by_count":15},{"id":"2001.05070","title":"Understanding Generalization in Deep Learning via Tensor Methods","created":"2020-01-14","cited_by_count":14},{"id":"1905.11428","title":"Equivalent and Approximate Transformations of Deep Neural Networks","created":"2019-05-27","cited_by_count":11},{"id":"2007.06567","title":"Lossless Compression of Structured Convolutional Models via Lifting","created":"2020-07-13","cited_by_count":11},{"id":"1805.10352","title":"Tensorial Neural Networks: Generalization of Neural Networks and Application to Model Compression","created":"2018-05-25","cited_by_count":9},{"id":"1711.00455","title":"A Unified View of Piecewise Linear Neural Network Verification","created":"2017-11-01","cited_by_count":7},{"id":"1808.08558","title":"Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error","created":"2018-08-26","cited_by_count":4}],"next_cursor":null}