{"list":"other","total":74,"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":"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":"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":"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":"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":"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":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"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":"1811.00250","title":"Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration","created":"2018-11-01","cited_by_count":367},{"id":"1808.06866","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","created":"2018-08-21","cited_by_count":315},{"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":"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":"1608.04493","title":"Dynamic Network Surgery for Efficient DNNs","created":"2016-08-16","cited_by_count":233},{"id":"1711.05908","title":"NISP: Pruning Networks using Neuron Importance Score Propagation","created":"2017-11-16","cited_by_count":228},{"id":"1903.10258","title":"MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning","created":"2019-03-25","cited_by_count":227},{"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":"1412.6553","title":"Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition","created":"2014-12-19","cited_by_count":203},{"id":"1511.06530","title":"Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications","created":"2015-11-20","cited_by_count":162},{"id":"2002.03231","title":"Soft Threshold Weight Reparameterization for Learnable Sparsity","created":"2020-02-08","cited_by_count":151},{"id":"1504.04788","title":"Compressing Neural Networks with the Hashing Trick","created":"2015-04-19","cited_by_count":150},{"id":"2006.07253","title":"Dynamic Model Pruning with Feedback","created":"2020-06-12","cited_by_count":125},{"id":"1802.00124","title":"Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers","created":"2018-02-01","cited_by_count":112},{"id":"1511.06067","title":"Convolutional neural networks with low-rank regularization","created":"2015-11-19","cited_by_count":103},{"id":"1810.07896","title":"Solving Linear Programs in the Current Matrix Multiplication Time","created":"2018-10-18","cited_by_count":100},{"id":"1702.04008","title":"Soft Weight-Sharing for Neural Network Compression","created":"2017-02-13","cited_by_count":99},{"id":"1911.07412","title":"Provable Filter Pruning for Efficient Neural Networks","created":"2019-11-18","cited_by_count":98},{"id":"1807.04518","title":"Turning Big data into tiny data: Constant-size coresets for k-means, PCA and projective clustering","created":"2018-07-12","cited_by_count":94},{"id":"1506.02515","title":"Fast ConvNets Using Group-wise Brain Damage","created":"2015-06-08","cited_by_count":82},{"id":"1605.06423","title":"Coresets for Scalable Bayesian Logistic Regression","created":"2016-05-20","cited_by_count":79},{"id":"1805.08941","title":"AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inference","created":"2018-05-23","cited_by_count":77},{"id":"2007.03938","title":"Operation-Aware Soft Channel Pruning using Differentiable Masks","created":"2020-07-08","cited_by_count":74},{"id":"1909.12579","title":"Pruning from Scratch","created":"2019-09-27","cited_by_count":72},{"id":"2003.01794","title":"Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection","created":"2020-03-03","cited_by_count":70},{"id":"1805.08571","title":"On Coresets for Logistic Regression","created":"2018-05-22","cited_by_count":67},{"id":"1703.08651","title":"More is Less: A More Complicated Network with Less Inference Complexity","created":"2017-03-25","cited_by_count":66},{"id":"1601.00617","title":"Coresets and Sketches","created":"2016-01-04","cited_by_count":63},{"id":"1908.08932","title":"Learning Filter Basis for Convolutional Neural Network Compression","created":"2019-08-23","cited_by_count":57},{"id":"1711.02638","title":"Compression-aware Training of Deep Networks","created":"2017-11-07","cited_by_count":46},{"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":"1612.00889","title":"New Frameworks for Offline and Streaming Coreset Constructions","created":"2016-12-02","cited_by_count":38},{"id":"2006.05482","title":"Coresets for Near-Convex Functions","created":"2020-06-09","cited_by_count":38},{"id":"2107.11442","title":"Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition","created":"2021-07-23","cited_by_count":33},{"id":"1906.04845","title":"Discrepancy, Coresets, and Sketches in Machine Learning","created":"2019-06-11","cited_by_count":30},{"id":"2106.04254","title":"Coresets for Classification -- Simplified and Strengthened","created":"2021-06-08","cited_by_count":28},{"id":"1511.05077","title":"Diversity Networks: Neural Network Compression Using Determinantal Point Processes","created":"2015-11-16","cited_by_count":25},{"id":"1511.06744","title":"Training CNNs with Low-Rank Filters for Efficient Image Classification","created":"2015-11-20","cited_by_count":25},{"id":"2004.14340","title":"WoodFisher: Efficient Second-Order Approximation for Neural Network Compression","created":"2020-04-29","cited_by_count":21},{"id":"2002.06469","title":"On Coresets for Support Vector Machines","created":"2020-02-15","cited_by_count":19},{"id":"2003.04135","title":"Sets Clustering","created":"2020-03-09","cited_by_count":19},{"id":"2111.03044","title":"A Unified Approach to Coreset Learning","created":"2021-11-04","cited_by_count":18},{"id":"1910.05422","title":"SiPPing Neural Networks: Sensitivity-informed Provable Pruning of Neural Networks","created":"2019-10-11","cited_by_count":17},{"id":"1910.08707","title":"Introduction to Coresets: Accurate Coresets","created":"2019-10-19","cited_by_count":17},{"id":"2008.08316","title":"Data-Independent Structured Pruning of Neural Networks via Coresets","created":"2020-08-19","cited_by_count":17},{"id":"2203.04370","title":"New Coresets for Projective Clustering and Applications","created":"2022-03-08","cited_by_count":16},{"id":"1711.09649","title":"One-Shot Coresets: The Case of k-Clustering","created":"2017-11-27","cited_by_count":15},{"id":"1508.05243","title":"Strong Coresets for Hard and Soft Bregman Clustering with Applications to Exponential Family Mixtures","created":"2015-08-21","cited_by_count":12},{"id":"1906.04705","title":"Fast and Accurate Least-Mean-Squares Solvers","created":"2019-06-11","cited_by_count":10},{"id":"2010.04290","title":"Deep Learning Meets Projective Clustering","created":"2020-10-08","cited_by_count":10},{"id":"2110.03195","title":"Coresets for Decision Trees of Signals","created":"2021-10-07","cited_by_count":10},{"id":"2001.03253","title":"Campfire: Compressible, Regularization-Free, Structured Sparse Training for Hardware Accelerators","created":"2020-01-09","cited_by_count":7},{"id":"2203.03009","title":"Coresets for Data Discretization and Sine Wave Fitting","created":"2022-03-06","cited_by_count":6},{"id":"2203.04075","title":"Obstacle Aware Sampling for Path Planning","created":"2022-03-08","cited_by_count":6},{"id":"2111.03046","title":"Introduction to Coresets: Approximated Mean","created":"2021-11-04","cited_by_count":5}],"next_cursor":null}