{"list":"other","total":101,"rows":[{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"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":"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":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1812.07956","title":"On Lazy Training in Differentiable Programming","created":"2018-12-19","cited_by_count":675},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"1711.00165","title":"Deep Neural Networks as Gaussian Processes","created":"2017-11-01","cited_by_count":622},{"id":"1610.01145","title":"Error bounds for approximations with deep ReLU networks","created":"2016-10-03","cited_by_count":574},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1901.08584","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","created":"2019-01-24","cited_by_count":566},{"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":"1511.02222","title":"Deep Kernel Learning","created":"2015-11-06","cited_by_count":445},{"id":"1805.09545","title":"On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport","created":"2018-05-24","cited_by_count":426},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"1412.8690","title":"Breaking the Curse of Dimensionality with Convex Neural Networks","created":"2014-12-30","cited_by_count":331},{"id":"1705.09280","title":"Implicit Regularization in Matrix Factorization","created":"2017-05-25","cited_by_count":322},{"id":"1804.11271","title":"Gaussian Process Behaviour in Wide Deep Neural Networks","created":"2018-04-30","cited_by_count":317},{"id":"2002.09277","title":"Kernel and Rich Regimes in Overparametrized Models","created":"2020-02-20","cited_by_count":306},{"id":"1503.00036","title":"Norm-Based Capacity Control in Neural Networks","created":"2015-02-27","cited_by_count":299},{"id":"1712.06541","title":"Size-Independent Sample Complexity of Neural Networks","created":"2017-12-18","cited_by_count":290},{"id":"1602.04485","title":"Benefits of depth in neural networks","created":"2016-02-14","cited_by_count":250},{"id":"1605.07110","title":"Deep Learning without Poor Local Minima","created":"2016-05-23","cited_by_count":234},{"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":"1512.03965","title":"The Power of Depth for Feedforward Neural Networks","created":"2015-12-12","cited_by_count":183},{"id":"1810.02032","title":"Gradient descent aligns the layers of deep linear networks","created":"2018-10-04","cited_by_count":182},{"id":"1902.04674","title":"Towards moderate overparameterization: global convergence guarantees for training shallow neural networks","created":"2019-02-12","cited_by_count":176},{"id":"2106.10165","title":"The Principles of Deep Learning Theory","created":"2021-06-18","cited_by_count":173},{"id":"1810.05148","title":"Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes","created":"2018-10-11","cited_by_count":167},{"id":"2007.15801","title":"Finite Versus Infinite Neural Networks: an Empirical Study","created":"2020-07-31","cited_by_count":157},{"id":"2006.13409","title":"When Do Neural Networks Outperform Kernel Methods?","created":"2020-06-24","cited_by_count":150},{"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":"2205.01445","title":"High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation","created":"2022-05-03","cited_by_count":150},{"id":"1811.08888","title":"Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks","created":"2018-11-21","cited_by_count":141},{"id":"1502.06800","title":"On the Equivalence between Kernel Quadrature Rules and Random Feature Expansions","created":"2015-02-24","cited_by_count":138},{"id":"1602.05897","title":"Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity","created":"2016-02-18","cited_by_count":138},{"id":"1808.05587","title":"Deep Convolutional Networks as shallow Gaussian Processes","created":"2018-08-16","cited_by_count":138},{"id":"1810.05369","title":"Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel","created":"2018-10-12","cited_by_count":131},{"id":"2010.01092","title":"On the linearity of large non-linear models: when and why the tangent kernel is constant","created":"2020-10-02","cited_by_count":129},{"id":"1904.13262","title":"Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks","created":"2019-04-30","cited_by_count":124},{"id":"1909.05989","title":"Finite Depth and Width Corrections to the Neural Tangent Kernel","created":"2019-09-13","cited_by_count":115},{"id":"1910.01635","title":"A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case","created":"2019-10-03","cited_by_count":114},{"id":"1805.00915","title":"Trainability and Accuracy of Neural Networks: An Interacting Particle System Approach","created":"2018-05-02","cited_by_count":106},{"id":"1902.05040","title":"How do infinite width bounded norm networks look in function space?","created":"2019-02-13","cited_by_count":106},{"id":"2205.09653","title":"Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks","created":"2022-05-19","cited_by_count":105},{"id":"1909.08156","title":"Dynamics of Deep Neural Networks and Neural Tangent Hierarchy","created":"2019-09-18","cited_by_count":96},{"id":"1906.08899","title":"Limitations of Lazy Training of Two-layers Neural Networks","created":"2019-06-21","cited_by_count":87},{"id":"2009.14397","title":"Deep Equals Shallow for ReLU Networks in Kernel Regimes","created":"2020-09-30","cited_by_count":85},{"id":"2106.15933","title":"Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training, Symmetry, and Sparsity","created":"2021-06-30","cited_by_count":85},{"id":"1910.01619","title":"Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks","created":"2019-10-03","cited_by_count":79},{"id":"1910.00019","title":"Non-Gaussian processes and neural networks at finite widths","created":"2019-09-30","cited_by_count":78},{"id":"1810.06397","title":"A Priori Estimates of the Population Risk for Two-layer Neural Networks","created":"2018-10-15","cited_by_count":76},{"id":"2009.10683","title":"Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS","created":"2020-09-22","cited_by_count":74},{"id":"1908.09375","title":"Theoretical Issues in Deep Networks: Approximation, Optimization and Generalization","created":"2019-08-25","cited_by_count":72},{"id":"2001.11443","title":"A Rigorous Framework for the Mean Field Limit of Multilayer Neural Networks","created":"2020-01-30","cited_by_count":68},{"id":"2007.07497","title":"Phase diagram for two-layer ReLU neural networks at infinite-width limit","created":"2020-07-15","cited_by_count":67},{"id":"2006.05982","title":"Representation formulas and pointwise properties for Barron functions","created":"2020-06-10","cited_by_count":62},{"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":"2105.03361","title":"What Kinds of Functions do Deep Neural Networks Learn? Insights from Variational Spline Theory","created":"2021-05-07","cited_by_count":60},{"id":"1610.09887","title":"Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks","created":"2016-10-31","cited_by_count":59},{"id":"2003.02237","title":"Neural Kernels Without Tangents","created":"2020-03-04","cited_by_count":56},{"id":"2003.05508","title":"A Mean-field Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth","created":"2020-03-11","cited_by_count":56},{"id":"2012.00152","title":"Every Model Learned by Gradient Descent Is Approximately a Kernel Machine","created":"2020-11-30","cited_by_count":55},{"id":"1702.08503","title":"SGD Learns the Conjugate Kernel Class of the Network","created":"2017-02-27","cited_by_count":54},{"id":"1712.05438","title":"Stochastic Particle Gradient Descent for Infinite Ensembles","created":"2017-12-14","cited_by_count":52},{"id":"1901.08572","title":"Width Provably Matters in Optimization for Deep Linear Neural Networks","created":"2019-01-24","cited_by_count":52},{"id":"2109.09710","title":"Understanding neural networks with reproducing kernel Banach spaces","created":"2021-09-20","cited_by_count":50},{"id":"1904.04326","title":"A Comparative Analysis of the Optimization and Generalization Property of Two-layer Neural Network and Random Feature Models Under Gradient Descent Dynamics","created":"2019-04-08","cited_by_count":49},{"id":"1406.3332","title":"Convolutional Kernel Networks","created":"2014-06-12","cited_by_count":47},{"id":"1702.08489","title":"Depth Separation for Neural Networks","created":"2017-02-27","cited_by_count":46},{"id":"2006.13436","title":"Towards Understanding Hierarchical Learning: Benefits of Neural Representations","created":"2020-06-24","cited_by_count":46},{"id":"1802.06093","title":"Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks","created":"2018-02-16","cited_by_count":44},{"id":"2007.01452","title":"Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks","created":"2020-07-03","cited_by_count":44},{"id":"1903.04440","title":"Mean Field Analysis of Deep Neural Networks","created":"2019-03-11","cited_by_count":42},{"id":"2005.13530","title":"On the Convergence of Gradient Descent Training for Two-layer ReLU-networks in the Mean Field Regime","created":"2020-05-27","cited_by_count":39},{"id":"2007.15623","title":"On the Banach spaces associated with multi-layer ReLU networks: Function representation, approximation theory and gradient descent dynamics","created":"2020-07-30","cited_by_count":39},{"id":"2010.01590","title":"Deep kernel processes","created":"2020-10-04","cited_by_count":34},{"id":"2003.01094","title":"On the Global Convergence of Training Deep Linear ResNets","created":"2020-03-02","cited_by_count":29},{"id":"1508.05133","title":"Steps Toward Deep Kernel Methods from Infinite Neural Networks","created":"2015-08-20","cited_by_count":28},{"id":"1702.07028","title":"On the ability of neural nets to express distributions","created":"2017-02-22","cited_by_count":26},{"id":"2105.04504","title":"Deep Neural Networks as Point Estimates for Deep Gaussian Processes","created":"2021-05-10","cited_by_count":26},{"id":"1902.02880","title":"Mean Field Limit of the Learning Dynamics of Multilayer Neural Networks","created":"2019-02-07","cited_by_count":25},{"id":"2105.14417","title":"Overparameterization of deep ResNet: zero loss and mean-field analysis","created":"2021-05-30","cited_by_count":24},{"id":"2210.00688","title":"On the infinite-depth limit of finite-width neural networks","created":"2022-10-03","cited_by_count":22},{"id":"2001.00921","title":"Wide Neural Networks with Bottlenecks are Deep Gaussian Processes","created":"2020-01-03","cited_by_count":20},{"id":"2211.16980","title":"Infinite-width limit of deep linear neural networks","created":"2022-11-29","cited_by_count":20},{"id":"2002.09852","title":"Training Linear Neural Networks: Non-Local Convergence and Complexity Results","created":"2020-02-23","cited_by_count":19},{"id":"2102.01621","title":"Depth separation beyond radial functions","created":"2021-02-02","cited_by_count":18},{"id":"2205.12101","title":"Empirical Phase Diagram for Three-layer Neural Networks with Infinite Width","created":"2022-05-24","cited_by_count":17},{"id":"2105.05228","title":"Global Convergence of Three-layer Neural Networks in the Mean Field Regime","created":"2021-05-11","cited_by_count":16},{"id":"2202.06438","title":"Learning from Randomly Initialized Neural Network Features","created":"2022-02-13","cited_by_count":12},{"id":"1508.01084","title":"Deep Convolutional Networks are Hierarchical Kernel Machines","created":"2015-08-05","cited_by_count":9},{"id":"2304.01063","title":"Depth Separation with Multilayer Mean-Field Networks","created":"2023-04-03","cited_by_count":9},{"id":"2003.05884","title":"Towards a General Theory of Infinite-Width Limits of Neural Classifiers","created":"2020-03-12","cited_by_count":7},{"id":"2106.04770","title":"Ghosts in Neural Networks: Existence, Structure and Role of Infinite-Dimensional Null Space","created":"2021-06-09","cited_by_count":7},{"id":"2110.15596","title":"Training Integrable Parameterizations of Deep Neural Networks in the Infinite-Width Limit","created":"2021-10-29","cited_by_count":7},{"id":"1703.07872","title":"Random Features for Compositional Kernels","created":"2017-03-22","cited_by_count":5},{"id":"1810.10798","title":"A Gaussian Process perspective on Convolutional Neural Networks","created":"2018-10-25","cited_by_count":4},{"id":"2210.16286","title":"A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks","created":"2022-10-28","cited_by_count":3}],"next_cursor":"100"}