{"list":"other","total":95,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"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":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"2008.08186","title":"Prevalence of Neural Collapse during the terminal phase of deep learning training","created":"2020-08-18","cited_by_count":719},{"id":"1812.07956","title":"On Lazy Training in Differentiable Programming","created":"2018-12-19","cited_by_count":675},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1902.06162","title":"Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey","created":"2019-02-16","cited_by_count":657},{"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":"1906.11300","title":"Benign Overfitting in Linear Regression","created":"2019-06-26","cited_by_count":549},{"id":"1908.05355","title":"The generalization error of random features regression: Precise asymptotics and double descent curve","created":"2019-08-14","cited_by_count":413},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"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":"1709.02540","title":"The Expressive Power of Neural Networks: A View from the Width","created":"2017-09-08","cited_by_count":320},{"id":"1906.05890","title":"Gradient Descent Maximizes the Margin of Homogeneous Neural Networks","created":"2019-06-13","cited_by_count":320},{"id":"1802.08246","title":"Characterizing Implicit Bias in Terms of Optimization Geometry","created":"2018-02-22","cited_by_count":266},{"id":"1806.00468","title":"Implicit Bias of Gradient Descent on Linear Convolutional Networks","created":"2018-06-01","cited_by_count":251},{"id":"1503.02101","title":"Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition","created":"2015-03-06","cited_by_count":243},{"id":"1605.07110","title":"Deep Learning without Poor Local Minima","created":"2016-05-23","cited_by_count":234},{"id":"1808.00387","title":"Just Interpolate: Kernel \"Ridgeless\" Regression Can Generalize","created":"2018-08-01","cited_by_count":190},{"id":"1806.05393","title":"Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks","created":"2018-06-14","cited_by_count":176},{"id":"1809.09573","title":"Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview","created":"2018-09-25","cited_by_count":160},{"id":"2002.03932","title":"Pre-training Tasks for Embedding-based Large-scale Retrieval","created":"2020-02-10","cited_by_count":153},{"id":"1712.06559","title":"The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning","created":"2017-12-18","cited_by_count":150},{"id":"2006.08558","title":"Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction","created":"2020-06-15","cited_by_count":142},{"id":"2011.11619","title":"Neural collapse with unconstrained features","created":"2020-11-23","cited_by_count":142},{"id":"2011.02803","title":"Intriguing Properties of Contrastive Losses","created":"2020-11-05","cited_by_count":130},{"id":"1704.00708","title":"No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis","created":"2017-04-03","cited_by_count":129},{"id":"1605.07272","title":"Matrix Completion has No Spurious Local Minimum","created":"2016-05-24","cited_by_count":125},{"id":"1904.13262","title":"Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks","created":"2019-04-30","cited_by_count":124},{"id":"2005.06398","title":"Implicit Regularization in Deep Learning May Not Be Explainable by Norms","created":"2020-05-13","cited_by_count":119},{"id":"1803.01905","title":"Convergence of Gradient Descent on Separable Data","created":"2018-03-05","cited_by_count":110},{"id":"1611.04231","title":"Identity Matters in Deep Learning","created":"2016-11-14","cited_by_count":109},{"id":"2002.11328","title":"Rethinking Bias-Variance Trade-off for Generalization of Neural Networks","created":"2020-02-26","cited_by_count":107},{"id":"1712.08968","title":"Spurious Local Minima are Common in Two-Layer ReLU Neural Networks","created":"2017-12-24","cited_by_count":104},{"id":"2008.11865","title":"Traces of Class/Cross-Class Structure Pervade Deep Learning Spectra","created":"2020-08-27","cited_by_count":94},{"id":"1602.06664","title":"A Geometric Analysis of Phase Retrieval","created":"2016-02-22","cited_by_count":92},{"id":"2007.12826","title":"The Interpolation Phase Transition in Neural Networks: Memorization and Generalization under Lazy Training","created":"2020-07-25","cited_by_count":84},{"id":"1605.07221","title":"Global Optimality of Local Search for Low Rank Matrix Recovery","created":"2016-05-23","cited_by_count":82},{"id":"2001.05992","title":"Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks","created":"2020-01-16","cited_by_count":73},{"id":"2007.06738","title":"Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy","created":"2020-07-13","cited_by_count":71},{"id":"1712.01473","title":"Deep linear neural networks with arbitrary loss: All local minima are global","created":"2017-12-05","cited_by_count":65},{"id":"1806.01796","title":"Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning Rate","created":"2018-06-05","cited_by_count":64},{"id":"1509.07385","title":"Provable approximation properties for deep neural networks","created":"2015-09-24","cited_by_count":60},{"id":"2006.11226","title":"Gradient descent follows the regularization path for general losses","created":"2020-06-19","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":"2002.09773","title":"Revealing the Structure of Deep Neural Networks via Convex Duality","created":"2020-02-22","cited_by_count":54},{"id":"2012.08465","title":"Neural Collapse with Cross-Entropy Loss","created":"2020-12-15","cited_by_count":52},{"id":"1511.03607","title":"Complete Dictionary Recovery over the Sphere I: Overview and the Geometric Picture","created":"2015-11-11","cited_by_count":49},{"id":"2102.02410","title":"A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network","created":"2021-02-04","cited_by_count":47},{"id":"1901.08168","title":"Loss Landscapes of Regularized Linear Autoencoders","created":"2019-01-23","cited_by_count":46},{"id":"1802.05374","title":"A Progressive Batching L-BFGS Method for Machine Learning","created":"2018-02-15","cited_by_count":45},{"id":"2004.04690","title":"Orthogonal Over-Parameterized Training","created":"2020-04-09","cited_by_count":44},{"id":"1801.04540","title":"Fix your classifier: the marginal value of training the last weight layer","created":"2018-01-14","cited_by_count":43},{"id":"2006.16992","title":"Deep Isometric Learning for Visual Recognition","created":"2020-06-30","cited_by_count":39},{"id":"1702.07945","title":"Global Optimality in Low-rank Matrix Optimization","created":"2017-02-25","cited_by_count":36},{"id":"2008.11245","title":"Deep Networks and the Multiple Manifold Problem","created":"2020-08-25","cited_by_count":35},{"id":"1707.02444","title":"Global optimality conditions for deep neural networks","created":"2017-07-08","cited_by_count":31},{"id":"2012.06188","title":"Recent Theoretical Advances in Non-Convex Optimization","created":"2020-12-11","cited_by_count":30},{"id":"2012.10424","title":"Separation and Concentration in Deep Networks","created":"2020-12-18","cited_by_count":30},{"id":"2007.00028","title":"Gradient Methods Never Overfit On Separable Data","created":"2020-06-30","cited_by_count":29},{"id":"2007.06753","title":"From Symmetry to Geometry: Tractable Nonconvex Problems","created":"2020-07-14","cited_by_count":29},{"id":"1510.06096","title":"When Are Nonconvex Problems Not Scary?","created":"2015-10-21","cited_by_count":28},{"id":"1802.03487","title":"Small nonlinearities in activation functions create bad local minima in neural networks","created":"2018-02-10","cited_by_count":28},{"id":"2006.08857","title":"Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization","created":"2020-06-16","cited_by_count":26},{"id":"1511.04777","title":"Complete Dictionary Recovery over the Sphere II: Recovery by Riemannian Trust-region Method","created":"2015-11-15","cited_by_count":24},{"id":"1506.07540","title":"Global Optimality in Tensor Factorization, Deep Learning, and Beyond","created":"2015-06-24","cited_by_count":22},{"id":"2010.12088","title":"Adversarial Robustness of Supervised Sparse Coding","created":"2020-10-22","cited_by_count":22},{"id":"1805.08671","title":"Adding One Neuron Can Eliminate All Bad Local Minima","created":"2018-05-22","cited_by_count":21},{"id":"1412.4659","title":"Finding a sparse vector in a subspace: Linear sparsity using alternating directions","created":"2014-12-15","cited_by_count":18},{"id":"2008.02901","title":"Benign Overfitting and Noisy Features","created":"2020-08-06","cited_by_count":18},{"id":"2102.12238","title":"Inductive Bias of Multi-Channel Linear Convolutional Networks with Bounded Weight Norm","created":"2021-02-24","cited_by_count":18},{"id":"1906.03559","title":"The Implicit Bias of AdaGrad on Separable Data","created":"2019-06-09","cited_by_count":16},{"id":"1806.00338","title":"Structured Local Optima in Sparse Blind Deconvolution","created":"2018-06-01","cited_by_count":15},{"id":"2103.00673","title":"Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training","created":"2021-03-01","cited_by_count":15},{"id":"2001.06970","title":"Finding the Sparsest Vectors in a Subspace: Theory, Algorithms, and Applications","created":"2020-01-20","cited_by_count":13},{"id":"1604.04112","title":"Deep Residual Networks with Exponential Linear Unit","created":"2016-04-14","cited_by_count":12},{"id":"1805.04938","title":"The Global Optimization Geometry of Shallow Linear Neural Networks","created":"2018-05-13","cited_by_count":11},{"id":"1901.00256","title":"Geometry and Symmetry in Short-and-Sparse Deconvolution","created":"2019-01-02","cited_by_count":11},{"id":"1803.02968","title":"Learning Deep Models: Critical Points and Local Openness","created":"2018-03-08","cited_by_count":10},{"id":"2010.14765","title":"Deep Networks from the Principle of Rate Reduction","created":"2020-10-27","cited_by_count":10},{"id":"1908.10959","title":"Short-and-Sparse Deconvolution -- A Geometric Approach","created":"2019-08-28","cited_by_count":9},{"id":"1706.08934","title":"Reexamining Low Rank Matrix Factorization for Trace Norm Regularization","created":"2017-06-27","cited_by_count":3}],"next_cursor":null}