{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"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":"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":"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":"1412.8690","title":"Breaking the Curse of Dimensionality with Convex Neural Networks","created":"2014-12-30","cited_by_count":331},{"id":"2002.09277","title":"Kernel and Rich Regimes in Overparametrized Models","created":"2020-02-20","cited_by_count":306},{"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":"1905.13210","title":"Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks","created":"2019-05-30","cited_by_count":222},{"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":"1512.03965","title":"The Power of Depth for Feedforward Neural Networks","created":"2015-12-12","cited_by_count":183},{"id":"1902.04674","title":"Towards moderate overparameterization: global convergence guarantees for training shallow neural networks","created":"2019-02-12","cited_by_count":176},{"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":"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":"1502.06800","title":"On the Equivalence between Kernel Quadrature Rules and Random Feature Expansions","created":"2015-02-24","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":"1808.09372","title":"Mean Field Analysis of Neural Networks: A Central Limit Theorem","created":"2018-08-28","cited_by_count":107},{"id":"1805.00915","title":"Trainability and Accuracy of Neural Networks: An Interacting Particle System Approach","created":"2018-05-02","cited_by_count":106},{"id":"1906.08899","title":"Limitations of Lazy Training of Two-layers Neural Networks","created":"2019-06-21","cited_by_count":87},{"id":"1911.12360","title":"How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks?","created":"2019-11-27","cited_by_count":84},{"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":"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":"2202.01009","title":"Mean-Field Langevin Dynamics: Exponential Convergence and Annealing","created":"2022-02-02","cited_by_count":61},{"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":"2201.10469","title":"Convex Analysis of the Mean Field Langevin Dynamics","created":"2022-01-25","cited_by_count":55},{"id":"1712.05438","title":"Stochastic Particle Gradient Descent for Infinite Ensembles","created":"2017-12-14","cited_by_count":52},{"id":"1905.07769","title":"Mean-Field Langevin Dynamics and Energy Landscape of Neural Networks","created":"2019-05-19","cited_by_count":50},{"id":"1907.10300","title":"Sparse Optimization on Measures with Over-parameterized Gradient Descent","created":"2019-07-24","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":"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":"1901.01375","title":"Analysis of a Two-Layer Neural Network via Displacement Convexity","created":"2019-01-05","cited_by_count":27},{"id":"2105.02095","title":"Two-layer neural networks with values in a Banach space","created":"2021-05-05","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":"2005.10815","title":"Can Shallow Neural Networks Beat the Curse of Dimensionality? A mean field training perspective","created":"2020-05-21","cited_by_count":22},{"id":"2012.15477","title":"Particle Dual Averaging: Optimization of Mean Field Neural Networks with Global Convergence Rate Analysis","created":"2020-12-31","cited_by_count":21},{"id":"2007.06352","title":"Quantitative Propagation of Chaos for SGD in Wide Neural Networks","created":"2020-07-13","cited_by_count":20},{"id":"2112.02393","title":"Optimization-Based Separations for Neural Networks","created":"2021-12-04","cited_by_count":17},{"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":"2110.15954","title":"Limiting fluctuation and trajectorial stability of multilayer neural networks with mean field training","created":"2021-10-29","cited_by_count":5}],"next_cursor":null}