{"list":"other","total":60,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"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":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1902.06720","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","created":"2019-02-18","cited_by_count":738},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"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":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"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":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"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":"1705.07565","title":"Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon","created":"2017-05-22","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":"2101.08134","title":"Zero-Cost Proxies for Lightweight NAS","created":"2021-01-20","cited_by_count":199},{"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":"2102.11535","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","created":"2021-02-23","cited_by_count":169},{"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":"1711.05136","title":"Deep Rewiring: Training very sparse deep networks","created":"2017-11-14","cited_by_count":139},{"id":"1711.04735","title":"Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice","created":"2017-11-13","cited_by_count":132},{"id":"1707.04926","title":"Theoretical insights into the optimization landscape of over-parameterized shallow neural networks","created":"2017-07-16","cited_by_count":128},{"id":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110},{"id":"1712.08968","title":"Spurious Local Minima are Common in Two-Layer ReLU Neural Networks","created":"2017-12-24","cited_by_count":104},{"id":"1912.04427","title":"Winning the Lottery with Continuous Sparsification","created":"2019-12-10","cited_by_count":100},{"id":"1906.06307","title":"A Signal Propagation Perspective for Pruning Neural Networks at Initialization","created":"2019-06-14","cited_by_count":96},{"id":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84},{"id":"2010.03533","title":"Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win","created":"2020-10-07","cited_by_count":77},{"id":"1802.09979","title":"The Emergence of Spectral Universality in Deep Networks","created":"2018-02-27","cited_by_count":74},{"id":"2007.03938","title":"Operation-Aware Soft Channel Pruning using Differentiable Masks","created":"2020-07-08","cited_by_count":74},{"id":"1611.06694","title":"Training Sparse Neural Networks","created":"2016-11-21","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":"2006.09081","title":"Progressive Skeletonization: Trimming more fat from a network at initialization","created":"2020-06-16","cited_by_count":64},{"id":"1802.10399","title":"Compressing Neural Networks using the Variational Information Bottleneck","created":"2018-02-28","cited_by_count":59},{"id":"2007.01429","title":"The Global Landscape of Neural Networks: An Overview","created":"2020-07-02","cited_by_count":57},{"id":"2105.01571","title":"Effective Sparsification of Neural Networks with Global Sparsity Constraint","created":"2021-05-03","cited_by_count":45},{"id":"2202.08132","title":"Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients","created":"2022-02-16","cited_by_count":34},{"id":"1905.10826","title":"On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective","created":"2019-05-26","cited_by_count":28},{"id":"2006.08228","title":"Finding trainable sparse networks through Neural Tangent Transfer","created":"2020-06-15","cited_by_count":28},{"id":"2109.00817","title":"NASI: Label- and Data-agnostic Neural Architecture Search at Initialization","created":"2021-09-02","cited_by_count":28},{"id":"1803.00909","title":"Understanding the Loss Surface of Neural Networks for Binary Classification","created":"2018-02-19","cited_by_count":27},{"id":"2101.09048","title":"Selfish Sparse RNN Training","created":"2021-01-22","cited_by_count":26},{"id":"2203.09137","title":"Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning","created":"2022-03-17","cited_by_count":22},{"id":"1802.06384","title":"Spurious Valleys in Two-layer Neural Network Optimization Landscapes","created":"2018-02-18","cited_by_count":21},{"id":"1805.08671","title":"Adding One Neuron Can Eliminate All Bad Local Minima","created":"2018-05-22","cited_by_count":21},{"id":"2011.04926","title":"Towards a Better Global Loss Landscape of GANs","created":"2020-11-10","cited_by_count":17},{"id":"1812.11039","title":"On the Benefit of Width for Neural Networks: Disappearance of Bad Basins","created":"2018-12-28","cited_by_count":16},{"id":"2210.12001","title":"When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work","created":"2022-10-21","cited_by_count":8},{"id":"1912.13472","title":"Revisiting Landscape Analysis in Deep Neural Networks: Eliminating Decreasing Paths to Infinity","created":"2019-12-31","cited_by_count":6},{"id":"2009.07439","title":"On the Landscape of One-hidden-layer Sparse Networks and Beyond","created":"2020-09-16","cited_by_count":3},{"id":"2104.11895","title":"Achieving Small Test Error in Mildly Overparameterized Neural Networks","created":"2021-04-24","cited_by_count":3}],"next_cursor":null}