{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1601.06759","title":"Pixel Recurrent Neural Networks","created":"2016-01-25","cited_by_count":816},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"1804.06561","title":"A Mean Field View of the Landscape of Two-Layers Neural Networks","created":"2018-04-18","cited_by_count":466},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"1412.5567","title":"Deep Speech: Scaling up end-to-end speech recognition","created":"2014-12-17","cited_by_count":354},{"id":"1412.6614","title":"In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning","created":"2014-12-20","cited_by_count":342},{"id":"2002.09277","title":"Kernel and Rich Regimes in Overparametrized Models","created":"2020-02-20","cited_by_count":306},{"id":"1810.02281","title":"A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks","created":"2018-10-04","cited_by_count":184},{"id":"1709.05289","title":"Optimal approximation of piecewise smooth functions using deep ReLU neural networks","created":"2017-09-15","cited_by_count":179},{"id":"1902.04674","title":"Towards moderate overparameterization: global convergence guarantees for training shallow neural networks","created":"2019-02-12","cited_by_count":176},{"id":"1705.09886","title":"Convergence Analysis of Two-layer Neural Networks with ReLU Activation","created":"2017-05-28","cited_by_count":137},{"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":"1706.03175","title":"Recovery Guarantees for One-hidden-layer Neural Networks","created":"2017-06-10","cited_by_count":94},{"id":"1901.02220","title":"Deep Neural Network Approximation Theory","created":"2019-01-08","cited_by_count":93},{"id":"1705.01714","title":"Optimal Approximation with Sparsely Connected Deep Neural Networks","created":"2017-05-04","cited_by_count":91},{"id":"1910.00744","title":"Reverse-Engineering Deep ReLU Networks","created":"2019-10-02","cited_by_count":83},{"id":"1810.07770","title":"Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity","created":"2018-10-17","cited_by_count":78},{"id":"2007.06738","title":"Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy","created":"2020-07-13","cited_by_count":71},{"id":"1912.08957","title":"Optimization for deep learning: theory and algorithms","created":"2019-12-19","cited_by_count":70},{"id":"2003.01794","title":"Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection","created":"2020-03-03","cited_by_count":70},{"id":"2002.07867","title":"Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology","created":"2020-02-18","cited_by_count":66},{"id":"1608.03287","title":"Deep vs. shallow networks : An approximation theory perspective","created":"2016-08-10","cited_by_count":63},{"id":"1702.07966","title":"Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs","created":"2017-02-26","cited_by_count":61},{"id":"1910.05505","title":"Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers","created":"2019-10-12","cited_by_count":61},{"id":"1509.07385","title":"Provable approximation properties for deep neural networks","created":"2015-09-24","cited_by_count":60},{"id":"1705.04591","title":"Learning ReLUs via Gradient Descent","created":"2017-05-10","cited_by_count":54},{"id":"1703.00560","title":"An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis","created":"2017-03-02","cited_by_count":52},{"id":"1806.07808","title":"Learning One-hidden-layer ReLU Networks via Gradient Descent","created":"2018-06-20","cited_by_count":50},{"id":"1809.03062","title":"Analysis of the Generalization Error: Empirical Risk Minimization over Deep Artificial Neural Networks Overcomes the Curse of Dimensionality in the Numerical Approximation of Black-Scholes Partial Differential Equations","created":"2018-09-09","cited_by_count":45},{"id":"1905.02199","title":"Nonlinear Approximation and (Deep) ReLU Networks","created":"2019-05-05","cited_by_count":45},{"id":"1410.7660","title":"Non-convex Robust PCA","created":"2014-10-28","cited_by_count":41},{"id":"1712.00779","title":"Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima","created":"2017-12-03","cited_by_count":40},{"id":"1912.10095","title":"Landscape Connectivity and Dropout Stability of SGD Solutions for Over-parameterized Neural Networks","created":"2019-12-20","cited_by_count":35},{"id":"1802.06463","title":"Guaranteed Recovery of One-Hidden-Layer Neural Networks via Cross Entropy","created":"2018-02-18","cited_by_count":22},{"id":"1402.5180","title":"Guaranteed Non-Orthogonal Tensor Decomposition via Alternating Rank-$1$ Updates","created":"2014-02-21","cited_by_count":21},{"id":"1709.06129","title":"When is a Convolutional Filter Easy To Learn?","created":"2017-09-18","cited_by_count":21},{"id":"2006.11727","title":"Affine symmetries and neural network identifiability","created":"2020-06-21","cited_by_count":18},{"id":"1802.07301","title":"On the Connection Between Learning Two-Layers Neural Networks and Tensor Decomposition","created":"2018-02-20","cited_by_count":14},{"id":"1906.06994","title":"Neural network identifiability for a family of sigmoidal nonlinearities","created":"2019-06-11","cited_by_count":14},{"id":"1912.04007","title":"Subspace power method for symmetric tensor decomposition","created":"2019-12-09","cited_by_count":14},{"id":"1905.12882","title":"Function approximation by deep networks","created":"2019-05-30","cited_by_count":10},{"id":"1907.00485","title":"Robust and Resource Efficient Identification of Two Hidden Layer Neural Networks","created":"2019-06-30","cited_by_count":10},{"id":"2008.02545","title":"A deep network construction that adapts to intrinsic dimensionality beyond the domain","created":"2020-08-06","cited_by_count":10}],"next_cursor":null}