{"list":"other","total":53,"rows":[{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"1312.6120","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","created":"2013-12-20","cited_by_count":763},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"1610.01145","title":"Error bounds for approximations with deep ReLU networks","created":"2016-10-03","cited_by_count":574},{"id":"1906.11300","title":"Benign Overfitting in Linear Regression","created":"2019-06-26","cited_by_count":549},{"id":"1903.08560","title":"Surprises in High-Dimensional Ridgeless Least Squares Interpolation","created":"2019-03-19","cited_by_count":513},{"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":"1708.06633","title":"Nonparametric regression using deep neural networks with ReLU activation function","created":"2017-08-22","cited_by_count":433},{"id":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"1707.09564","title":"A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks","created":"2017-07-29","cited_by_count":314},{"id":"1703.02930","title":"Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks","created":"2017-03-08","cited_by_count":311},{"id":"1606.05336","title":"On the Expressive Power of Deep Neural Networks","created":"2016-06-16","cited_by_count":306},{"id":"1712.06541","title":"Size-Independent Sample Complexity of Neural Networks","created":"2017-12-18","cited_by_count":290},{"id":"1808.01204","title":"Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data","created":"2018-08-03","cited_by_count":261},{"id":"1905.13210","title":"Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks","created":"2019-05-30","cited_by_count":222},{"id":"1808.00387","title":"Just Interpolate: Kernel \"Ridgeless\" Regression Can Generalize","created":"2018-08-01","cited_by_count":190},{"id":"1709.05289","title":"Optimal approximation of piecewise smooth functions using deep ReLU neural networks","created":"2017-09-15","cited_by_count":179},{"id":"1805.10769","title":"Universality of Deep Convolutional Neural Networks","created":"2018-05-28","cited_by_count":176},{"id":"1611.00740","title":"Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review","created":"2016-11-02","cited_by_count":155},{"id":"2105.14368","title":"Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation","created":"2021-05-29","cited_by_count":132},{"id":"1903.09139","title":"Harmless interpolation of noisy data in regression","created":"2019-03-21","cited_by_count":121},{"id":"1906.04688","title":"An Improved Analysis of Training Over-parameterized Deep Neural Networks","created":"2019-06-11","cited_by_count":121},{"id":"1806.05161","title":"Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate","created":"2018-06-13","cited_by_count":99},{"id":"1911.12360","title":"How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks?","created":"2019-11-27","cited_by_count":84},{"id":"1905.10961","title":"Fast Convergence of Natural Gradient Descent for Overparameterized Neural Networks","created":"2019-05-27","cited_by_count":76},{"id":"1608.03287","title":"Deep vs. shallow networks : An approximation theory perspective","created":"2016-08-10","cited_by_count":63},{"id":"1509.07385","title":"Provable approximation properties for deep neural networks","created":"2015-09-24","cited_by_count":60},{"id":"1902.01384","title":"Generalization Error Bounds of Gradient Descent for Learning Over-parameterized Deep ReLU Networks","created":"2019-02-04","cited_by_count":60},{"id":"1802.04474","title":"Deep Neural Networks Learn Non-Smooth Functions Effectively","created":"2018-02-13","cited_by_count":57},{"id":"2007.01429","title":"The Global Landscape of Neural Networks: An Overview","created":"2020-07-02","cited_by_count":57},{"id":"1702.08503","title":"SGD Learns the Conjugate Kernel Class of the Network","created":"2017-02-27","cited_by_count":54},{"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":"1803.00225","title":"Global Convergence of Block Coordinate Descent in Deep Learning","created":"2018-03-01","cited_by_count":38},{"id":"1801.03437","title":"Approximation beats concentration? An approximation view on inference with smooth radial kernels","created":"2018-01-10","cited_by_count":33},{"id":"2007.00028","title":"Gradient Methods Never Overfit On Separable Data","created":"2020-06-30","cited_by_count":29},{"id":"2010.08479","title":"Failures of model-dependent generalization bounds for least-norm interpolation","created":"2020-10-16","cited_by_count":26},{"id":"1905.09870","title":"Gradient Descent can Learn Less Over-parameterized Two-layer Neural Networks on Classification Problems","created":"2019-05-23","cited_by_count":24},{"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":"1902.00800","title":"Complexity, Statistical Risk, and Metric Entropy of Deep Nets Using Total Path Variation","created":"2019-02-02","cited_by_count":16},{"id":"1910.02934","title":"Algorithm-Dependent Generalization Bounds for Overparameterized Deep Residual Networks","created":"2019-10-07","cited_by_count":16},{"id":"2004.00245","title":"Depth Selection for Deep ReLU Nets in Feature Extraction and Generalization","created":"2020-04-01","cited_by_count":13},{"id":"1803.03772","title":"Generalization and Expressivity for Deep Nets","created":"2018-03-10","cited_by_count":11},{"id":"1904.01814","title":"Deep Neural Networks for Rotation-Invariance Approximation and Learning","created":"2019-04-03","cited_by_count":10},{"id":"1912.07464","title":"Realization of spatial sparseness by deep ReLU nets with massive data","created":"2019-12-16","cited_by_count":10},{"id":"1901.00130","title":"Realizing data features by deep nets","created":"2019-01-01","cited_by_count":6},{"id":"2009.01514","title":"Kernel Interpolation of High Dimensional Scattered Data","created":"2020-09-03","cited_by_count":6},{"id":"2102.09804","title":"Local Convergence of Adaptive Gradient Descent Optimizers","created":"2021-02-19","cited_by_count":5},{"id":"1905.10686","title":"Empirical Risk Minimization in the Interpolating Regime with Application to Neural Network Learning","created":"2019-05-25","cited_by_count":2}],"next_cursor":null}