{"list":"other","total":52,"rows":[{"id":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"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":"1705.03341","title":"Stable Architectures for Deep Neural Networks","created":"2017-05-09","cited_by_count":341},{"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":"2003.04887","title":"ReZero is All You Need: Fast Convergence at Large Depth","created":"2020-03-10","cited_by_count":264},{"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":"1710.10121","title":"Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations","created":"2017-10-27","cited_by_count":203},{"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":"2006.07322","title":"Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks","created":"2020-06-12","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":"2012.11654","title":"Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks","created":"2020-12-21","cited_by_count":87},{"id":"2002.07867","title":"Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology","created":"2020-02-18","cited_by_count":66},{"id":"2002.06262","title":"Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? -- A Neural Tangent Kernel Perspective","created":"2020-02-14","cited_by_count":60},{"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":"1912.12777","title":"Machine Learning from a Continuous Viewpoint","created":"2019-12-30","cited_by_count":50},{"id":"2010.12859","title":"Stable ResNet","created":"2020-10-24","cited_by_count":49},{"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":"2106.04013","title":"The Future is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization","created":"2021-06-07","cited_by_count":33},{"id":"2205.14612","title":"Do Residual Neural Networks discretize Neural Ordinary Differential Equations?","created":"2022-05-29","cited_by_count":27},{"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":"2104.03093","title":"Spectral Analysis of the Neural Tangent Kernel for Deep Residual Networks","created":"2021-04-07","cited_by_count":21},{"id":"2302.00453","title":"Width and Depth Limits Commute in Residual Networks","created":"2023-02-01","cited_by_count":21},{"id":"2306.16361","title":"Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time","created":"2023-06-28","cited_by_count":20},{"id":"2309.01213","title":"Implicit regularization of deep residual networks towards neural ODEs","created":"2023-09-03","cited_by_count":20},{"id":"2009.10008","title":"Kernel-Based Smoothness Analysis of Residual Networks","created":"2020-09-21","cited_by_count":19},{"id":"2206.06929","title":"Scaling ResNets in the Large-depth Regime","created":"2022-06-14","cited_by_count":18},{"id":"1910.02934","title":"Algorithm-Dependent Generalization Bounds for Overparameterized Deep Residual Networks","created":"2019-10-07","cited_by_count":16},{"id":"1911.07626","title":"Convex Formulation of Overparameterized Deep Neural Networks","created":"2019-11-18","cited_by_count":16},{"id":"1912.05475","title":"Mean-Field Neural ODEs via Relaxed Optimal Control","created":"2019-12-11","cited_by_count":16},{"id":"2112.03657","title":"Understanding Square Loss in Training Overparametrized Neural Network Classifiers","created":"2021-12-07","cited_by_count":14},{"id":"2209.07238","title":"Generalization Properties of NAS under Activation and Skip Connection Search","created":"2022-09-15","cited_by_count":14},{"id":"2204.10782","title":"On Feature Learning in Neural Networks with Global Convergence Guarantees","created":"2022-04-22","cited_by_count":13},{"id":"2110.02926","title":"On the Global Convergence of Gradient Descent for multi-layer ResNets in the mean-field regime","created":"2021-10-06","cited_by_count":12},{"id":"2211.14810","title":"A Kernel Perspective of Skip Connections in Convolutional Networks","created":"2022-11-27","cited_by_count":12},{"id":"2205.14818","title":"Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods","created":"2022-05-30","cited_by_count":10},{"id":"2102.04998","title":"When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations?","created":"2021-02-09","cited_by_count":9},{"id":"2112.05531","title":"Global convergence of ResNets: From finite to infinite width using linear parameterization","created":"2021-12-10","cited_by_count":9},{"id":"1905.13654","title":"Exact Convergence Rates of the Neural Tangent Kernel in the Large Depth Limit","created":"2019-05-31","cited_by_count":5},{"id":"2204.07261","title":"Convergence and Implicit Regularization Properties of Gradient Descent for Deep Residual Networks","created":"2022-04-14","cited_by_count":3}],"next_cursor":null}