{"list":"other","total":54,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"1705.09280","title":"Implicit Regularization in Matrix Factorization","created":"2017-05-25","cited_by_count":322},{"id":"2002.09277","title":"Kernel and Rich Regimes in Overparametrized Models","created":"2020-02-20","cited_by_count":306},{"id":"1802.06509","title":"On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization","created":"2018-02-19","cited_by_count":284},{"id":"2002.04486","title":"Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss","created":"2020-02-11","cited_by_count":268},{"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":"1710.03667","title":"High-dimensional dynamics of generalization error in neural networks","created":"2017-10-10","cited_by_count":241},{"id":"1902.06015","title":"Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit","created":"2019-02-16","cited_by_count":187},{"id":"1810.02032","title":"Gradient descent aligns the layers of deep linear networks","created":"2018-10-04","cited_by_count":182},{"id":"1806.00900","title":"Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced","created":"2018-06-04","cited_by_count":177},{"id":"1809.09573","title":"Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview","created":"2018-09-25","cited_by_count":160},{"id":"2012.09839","title":"Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning","created":"2020-12-17","cited_by_count":150},{"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":"1906.08632","title":"Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup","created":"2019-06-18","cited_by_count":112},{"id":"1803.01905","title":"Convergence of Gradient Descent on Separable Data","created":"2018-03-05","cited_by_count":110},{"id":"1507.03566","title":"Low-rank Solutions of Linear Matrix Equations via Procrustes Flow","created":"2015-07-13","cited_by_count":97},{"id":"1509.05009","title":"On the Expressive Power of Deep Learning: A Tensor Analysis","created":"2015-09-16","cited_by_count":97},{"id":"1812.10004","title":"Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?","created":"2018-12-25","cited_by_count":88},{"id":"1809.10374","title":"An analytic theory of generalization dynamics and transfer learning in deep linear networks","created":"2018-09-27","cited_by_count":85},{"id":"2010.02501","title":"A Unifying View on Implicit Bias in Training Linear Neural Networks","created":"2020-10-06","cited_by_count":75},{"id":"1909.12051","title":"The Implicit Bias of Depth: How Incremental Learning Drives Generalization","created":"2019-09-26","cited_by_count":64},{"id":"2003.07802","title":"The Implicit Regularization of Stochastic Gradient Flow for Least Squares","created":"2020-03-17","cited_by_count":59},{"id":"1605.06743","title":"Inductive Bias of Deep Convolutional Networks through Pooling Geometry","created":"2016-05-22","cited_by_count":53},{"id":"1803.09780","title":"Quantum Entanglement in Deep Learning Architectures","created":"2018-03-26","cited_by_count":50},{"id":"1711.10105","title":"Tensor Completion Algorithms in Big Data Analytics","created":"2017-11-28","cited_by_count":48},{"id":"2012.05156","title":"Implicit Regularization in ReLU Networks with the Square Loss","created":"2020-12-09","cited_by_count":45},{"id":"1808.04295","title":"Understanding training and generalization in deep learning by Fourier analysis","created":"2018-08-13","cited_by_count":44},{"id":"2006.12467","title":"The Depth-to-Width Interplay in Self-Attention","created":"2020-06-22","cited_by_count":42},{"id":"2011.13772","title":"Gradient Descent for Deep Matrix Factorization: Dynamics and Implicit Bias towards Low Rank","created":"2020-11-27","cited_by_count":42},{"id":"1911.04436","title":"Nonconvex Low-Rank Tensor Completion from Noisy Data","created":"2019-11-11","cited_by_count":35},{"id":"1505.06611","title":"Smooth PARAFAC Decomposition for Tensor Completion","created":"2015-05-25","cited_by_count":34},{"id":"1603.00162","title":"Convolutional Rectifier Networks as Generalized Tensor Decompositions","created":"2016-03-01","cited_by_count":32},{"id":"1406.2784","title":"Provable Tensor Factorization with Missing Data","created":"2014-06-11","cited_by_count":31},{"id":"1711.00811","title":"Expressive power of recurrent neural networks","created":"2017-11-02","cited_by_count":30},{"id":"1702.06980","title":"On Polynomial Time Methods for Exact Low Rank Tensor Completion","created":"2017-02-22","cited_by_count":27},{"id":"1704.01552","title":"Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design","created":"2017-04-05","cited_by_count":24},{"id":"1911.07956","title":"Implicit Regularization and Convergence for Weight Normalization","created":"2019-11-18","cited_by_count":20},{"id":"2010.11356","title":"Beyond Lazy Training for Over-parameterized Tensor Decomposition","created":"2020-10-22","cited_by_count":15},{"id":"1710.09431","title":"On the Long-Term Memory of Deep Recurrent Networks","created":"2017-10-25","cited_by_count":14},{"id":"2001.05070","title":"Understanding Generalization in Deep Learning via Tensor Methods","created":"2020-01-14","cited_by_count":14},{"id":"1705.02302","title":"Analysis and Design of Convolutional Networks via Hierarchical Tensor Decompositions","created":"2017-05-05","cited_by_count":13},{"id":"1506.03059","title":"Deep SimNets","created":"2015-06-09","cited_by_count":10},{"id":"1901.10801","title":"Generalized Tensor Models for Recurrent Neural Networks","created":"2019-01-30","cited_by_count":8},{"id":"1410.0781","title":"SimNets: A Generalization of Convolutional Networks","created":"2014-10-03","cited_by_count":5},{"id":"1703.06846","title":"Boosting Dilated Convolutional Networks with Mixed Tensor Decompositions","created":"2017-03-20","cited_by_count":5},{"id":"2002.04710","title":"Unique Properties of Flat Minima in Deep Networks","created":"2020-02-11","cited_by_count":3},{"id":"2001.02370","title":"On Recoverability of Randomly Compressed Tensors with Low CP Rank","created":"2020-01-08","cited_by_count":2},{"id":"2002.09781","title":"An Optimization and Generalization Analysis for Max-Pooling Networks","created":"2020-02-22","cited_by_count":2}],"next_cursor":null}