{"list":"other","total":55,"rows":[{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"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":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"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":"1603.06560","title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","created":"2016-03-21","cited_by_count":699},{"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":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"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":"1807.01774","title":"BOHB: Robust and Efficient Hyperparameter Optimization at Scale","created":"2018-07-04","cited_by_count":470},{"id":"1707.04780","title":"Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science","created":"2017-07-15","cited_by_count":328},{"id":"2002.10179","title":"HRank: Filter Pruning using High-Rank Feature Map","created":"2020-02-24","cited_by_count":292},{"id":"1502.05700","title":"Scalable Bayesian Optimization Using Deep Neural Networks","created":"2015-02-19","cited_by_count":284},{"id":"1701.05369","title":"Variational Dropout Sparsifies Deep Neural Networks","created":"2017-01-19","cited_by_count":265},{"id":"1608.04493","title":"Dynamic Network Surgery for Efficient DNNs","created":"2016-08-16","cited_by_count":233},{"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":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"1902.05967","title":"Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization","created":"2019-02-15","cited_by_count":189},{"id":"2009.08576","title":"Pruning Neural Networks at Initialization: Why are We Missing the Mark?","created":"2020-09-18","cited_by_count":182},{"id":"1909.11957","title":"Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks","created":"2019-09-26","cited_by_count":160},{"id":"2002.03231","title":"Soft Threshold Weight Reparameterization for Learnable Sparsity","created":"2020-02-08","cited_by_count":151},{"id":"2107.05847","title":"Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges","created":"2021-07-13","cited_by_count":145},{"id":"1711.05136","title":"Deep Rewiring: Training very sparse deep networks","created":"2017-11-14","cited_by_count":139},{"id":"2006.07253","title":"Dynamic Model Pruning with Feedback","created":"2020-06-12","cited_by_count":125},{"id":"1902.09689","title":"AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks","created":"2019-02-26","cited_by_count":112},{"id":"1702.04008","title":"Soft Weight-Sharing for Neural Network Compression","created":"2017-02-13","cited_by_count":99},{"id":"1905.04226","title":"Language Modeling with Deep Transformers","created":"2019-05-10","cited_by_count":96},{"id":"1906.06307","title":"A Signal Propagation Perspective for Pruning Neural Networks at Initialization","created":"2019-06-14","cited_by_count":96},{"id":"1911.12409","title":"PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition","created":"2019-11-27","cited_by_count":91},{"id":"2106.03517","title":"Top-KAST: Top-K Always Sparse Training","created":"2021-06-07","cited_by_count":79},{"id":"1704.05119","title":"Exploring Sparsity in Recurrent Neural Networks","created":"2017-04-17","cited_by_count":75},{"id":"1904.12368","title":"Towards Efficient Model Compression via Learned Global Ranking","created":"2019-04-28","cited_by_count":75},{"id":"1802.09979","title":"The Emergence of Spectral Universality in Deep Networks","created":"2018-02-27","cited_by_count":74},{"id":"2005.06870","title":"Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers","created":"2020-05-14","cited_by_count":68},{"id":"1711.02017","title":"NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm","created":"2017-11-06","cited_by_count":60},{"id":"2103.06460","title":"Recent Advances on Neural Network Pruning at Initialization","created":"2021-03-11","cited_by_count":41},{"id":"1607.03474","title":"Recurrent Highway Networks","created":"2016-07-12","cited_by_count":37},{"id":"2006.02427","title":"Lyapunov spectra of chaotic recurrent neural networks","created":"2020-06-03","cited_by_count":37},{"id":"2006.14123","title":"On Lyapunov Exponents for RNNs: Understanding Information Propagation Using Dynamical Systems Tools","created":"2020-06-25","cited_by_count":31},{"id":"2207.06646","title":"DropNet: Reducing Neural Network Complexity via Iterative Pruning","created":"2022-07-14","cited_by_count":29},{"id":"1807.09810","title":"Coreset-Based Neural Network Compression","created":"2018-07-25","cited_by_count":27},{"id":"2101.09048","title":"Selfish Sparse RNN Training","created":"2021-01-22","cited_by_count":26},{"id":"1709.05027","title":"Learning Intrinsic Sparse Structures within Long Short-Term Memory","created":"2017-09-15","cited_by_count":18},{"id":"1612.06212","title":"A recurrent neural network without chaos","created":"2016-12-19","cited_by_count":13},{"id":"2008.03088","title":"Pretraining Techniques for Sequence-to-Sequence Voice Conversion","created":"2020-08-07","cited_by_count":13},{"id":"2003.11660","title":"R-FORCE: Robust Learning for Random Recurrent Neural Networks","created":"2020-03-25","cited_by_count":3},{"id":"2204.04876","title":"Lyapunov-Guided Representation of Recurrent Neural Network Performance","created":"2022-04-11","cited_by_count":3}],"next_cursor":null}