{"list":"other","total":63,"rows":[{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"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":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","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":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"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":"1807.06629","title":"Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning","created":"2018-07-17","cited_by_count":278},{"id":"1306.0543","title":"Predicting Parameters in Deep Learning","created":"2013-06-03","cited_by_count":224},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"1905.01067","title":"Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask","created":"2019-05-03","cited_by_count":207},{"id":"1808.07217","title":"Don't Use Large Mini-Batches, Use Local SGD","created":"2018-08-22","cited_by_count":202},{"id":"1710.09854","title":"Gradient Sparsification for Communication-Efficient Distributed Optimization","created":"2017-10-26","cited_by_count":201},{"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":"1802.09941","title":"Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis","created":"2018-02-26","cited_by_count":156},{"id":"2002.03231","title":"Soft Threshold Weight Reparameterization for Learnable Sparsity","created":"2020-02-08","cited_by_count":151},{"id":"1610.02132","title":"QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding","created":"2016-10-07","cited_by_count":147},{"id":"2006.10901","title":"Sparse GPU Kernels for Deep Learning","created":"2020-06-18","cited_by_count":141},{"id":"1711.05136","title":"Deep Rewiring: Training very sparse deep networks","created":"2017-11-14","cited_by_count":139},{"id":"1506.08272","title":"Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization","created":"2015-06-27","cited_by_count":116},{"id":"1507.06149","title":"Data-free parameter pruning for Deep Neural Networks","created":"2015-07-22","cited_by_count":112},{"id":"1902.06853","title":"On the Impact of the Activation Function on Deep Neural Networks Training","created":"2019-02-19","cited_by_count":102},{"id":"1609.08326","title":"Asynchronous Stochastic Gradient Descent with Delay Compensation","created":"2016-09-27","cited_by_count":99},{"id":"1906.06307","title":"A Signal Propagation Perspective for Pruning Neural Networks at Initialization","created":"2019-06-14","cited_by_count":96},{"id":"2010.03533","title":"Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win","created":"2020-10-07","cited_by_count":77},{"id":"1704.05119","title":"Exploring Sparsity in Recurrent Neural Networks","created":"2017-04-17","cited_by_count":75},{"id":"1805.12233","title":"How Important Is a Neuron?","created":"2018-05-30","cited_by_count":73},{"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":"2001.02312","title":"Stochastic Weight Averaging in Parallel: Large-Batch Training that Generalizes Well","created":"2020-01-07","cited_by_count":57},{"id":"1901.09181","title":"Sparse evolutionary Deep Learning with over one million artificial neurons on commodity hardware","created":"2019-01-26","cited_by_count":48},{"id":"2001.01969","title":"Sparse Weight Activation Training","created":"2020-01-07","cited_by_count":45},{"id":"1604.05978","title":"A topological insight into restricted Boltzmann machines","created":"2016-04-20","cited_by_count":32},{"id":"1606.07365","title":"Parallel SGD: When does averaging help?","created":"2016-06-23","cited_by_count":32},{"id":"1605.09774","title":"Asynchrony begets Momentum, with an Application to Deep Learning","created":"2016-05-31","cited_by_count":30},{"id":"2007.15353","title":"Growing Efficient Deep Networks by Structured Continuous Sparsification","created":"2020-07-30","cited_by_count":28},{"id":"1512.07030","title":"Deep Learning with S-shaped Rectified Linear Activation Units","created":"2015-12-22","cited_by_count":26},{"id":"2101.09048","title":"Selfish Sparse RNN Training","created":"2021-01-22","cited_by_count":26},{"id":"1905.09397","title":"Cognitive Model Priors for Predicting Human Decisions","created":"2019-05-22","cited_by_count":25},{"id":"1711.08757","title":"Deep Expander Networks: Efficient Deep Networks from Graph Theory","created":"2017-11-23","cited_by_count":23},{"id":"2006.14085","title":"Topological Insights into Sparse Neural Networks","created":"2020-06-24","cited_by_count":22},{"id":"1709.05027","title":"Learning Intrinsic Sparse Structures within Long Short-Term Memory","created":"2017-09-15","cited_by_count":18},{"id":"1905.00416","title":"RadiX-Net: Structured Sparse Matrices for Deep Neural Networks","created":"2019-04-30","cited_by_count":12},{"id":"1909.05631","title":"Sparse Deep Neural Network Graph Challenge","created":"2019-09-02","cited_by_count":7},{"id":"1810.00299","title":"Training Behavior of Sparse Neural Network Topologies","created":"2018-09-30","cited_by_count":6},{"id":"1911.03444","title":"MindTheStep-AsyncPSGD: Adaptive Asynchronous Parallel Stochastic Gradient Descent","created":"2019-11-08","cited_by_count":3},{"id":"2010.05943","title":"Activation function impact on Sparse Neural Networks","created":"2020-10-12","cited_by_count":3},{"id":"1304.6475","title":"Revisiting Asynchronous Linear Solvers: Provable Convergence Rate Through Randomization","created":"2013-04-24","cited_by_count":2},{"id":"1807.03165","title":"Sparse Deep Neural Network Exact Solutions","created":"2018-07-06","cited_by_count":2},{"id":"1809.09258","title":"Asynchronous decentralized accelerated stochastic gradient descent","created":"2018-09-24","cited_by_count":2},{"id":"1708.02937","title":"Enabling Massive Deep Neural Networks with the GraphBLAS","created":"2017-08-09","cited_by_count":1},{"id":"1712.05878","title":"An MPI-Based Python Framework for Distributed Training with Keras","created":"2017-12-16","cited_by_count":1}],"next_cursor":null}