{"list":"other","total":75,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"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":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"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":"1405.3866","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","created":"2014-05-15","cited_by_count":284},{"id":"1611.01491","title":"Understanding Deep Neural Networks with Rectified Linear Units","created":"2016-11-04","cited_by_count":257},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"1911.13299","title":"What's Hidden in a Randomly Weighted Neural Network?","created":"2019-11-29","cited_by_count":237},{"id":"2110.14430","title":"Adversarial Neuron Pruning Purifies Backdoored Deep Models","created":"2021-10-27","cited_by_count":235},{"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":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218},{"id":"1905.01067","title":"Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask","created":"2019-05-03","cited_by_count":207},{"id":"1412.6553","title":"Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition","created":"2014-12-19","cited_by_count":203},{"id":"2002.00585","title":"Proving the Lottery Ticket Hypothesis: Pruning is All You Need","created":"2020-02-03","cited_by_count":201},{"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":"2108.00708","title":"Group Fisher Pruning for Practical Network Compression","created":"2021-08-02","cited_by_count":131},{"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":"1911.07412","title":"Provable Filter Pruning for Efficient Neural Networks","created":"2019-11-18","cited_by_count":98},{"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":"1509.08101","title":"Representation Benefits of Deep Feedforward Networks","created":"2015-09-27","cited_by_count":86},{"id":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84},{"id":"1506.02515","title":"Fast ConvNets Using Group-wise Brain Damage","created":"2015-06-08","cited_by_count":82},{"id":"2006.07990","title":"Optimal Lottery Tickets via SubsetSum: Logarithmic Over-Parameterization is Sufficient","created":"2020-06-14","cited_by_count":81},{"id":"2006.12156","title":"Logarithmic Pruning is All You Need","created":"2020-06-22","cited_by_count":71},{"id":"2003.01794","title":"Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection","created":"2020-03-03","cited_by_count":70},{"id":"2107.07467","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","created":"2021-07-15","cited_by_count":70},{"id":"2103.03014","title":"Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy","created":"2021-03-04","cited_by_count":62},{"id":"2007.01429","title":"The Global Landscape of Neural Networks: An Overview","created":"2020-07-02","cited_by_count":57},{"id":"1802.09052","title":"Wide Compression: Tensor Ring Nets","created":"2018-02-25","cited_by_count":50},{"id":"2006.00978","title":"On the Number of Linear Regions of Convolutional Neural Networks","created":"2020-06-01","cited_by_count":49},{"id":"2110.14222","title":"Sample Selection for Fair and Robust Training","created":"2021-10-27","cited_by_count":48},{"id":"2106.03225","title":"Efficient Lottery Ticket Finding: Less Data is More","created":"2021-06-06","cited_by_count":44},{"id":"1804.05345","title":"Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization Bounds","created":"2018-04-15","cited_by_count":43},{"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":"2104.08135","title":"Sharp bounds for the number of regions of maxout networks and vertices of Minkowski sums","created":"2021-04-16","cited_by_count":37},{"id":"2001.00218","title":"Lossless Compression of Deep Neural Networks","created":"2020-01-01","cited_by_count":34},{"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":"2007.08243","title":"Lottery Tickets in Linear Models: An Analysis of Iterative Magnitude Pruning","created":"2020-07-16","cited_by_count":23},{"id":"2009.09936","title":"Prune Responsibly","created":"2020-09-10","cited_by_count":20},{"id":"2106.09269","title":"Pruning Randomly Initialized Neural Networks with Iterative Randomization","created":"2021-06-17","cited_by_count":20},{"id":"2102.07804","title":"Scaling Up Exact Neural Network Compression by ReLU Stability","created":"2021-02-15","cited_by_count":19},{"id":"1807.10585","title":"Filter Distillation for Network Compression","created":"2018-07-20","cited_by_count":17},{"id":"2105.10065","title":"A Probabilistic Approach to Neural Network Pruning","created":"2021-05-20","cited_by_count":15},{"id":"2107.00379","title":"On the Expected Complexity of Maxout Networks","created":"2021-07-01","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":"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":"2104.12835","title":"Less is more: Selecting informative and diverse subsets with balancing constraints","created":"2021-04-26","cited_by_count":5},{"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},{"id":"2111.08577","title":"Neuron-based Pruning of Deep Neural Networks with Better Generalization using Kronecker Factored Curvature Approximation","created":"2021-11-16","cited_by_count":4}],"next_cursor":null}