{"list":"other","total":75,"rows":[{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"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":"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":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"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":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"1402.1869","title":"On the Number of Linear Regions of Deep Neural Networks","created":"2014-02-08","cited_by_count":381},{"id":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"1906.05890","title":"Gradient Descent Maximizes the Margin of Homogeneous Neural Networks","created":"2019-06-13","cited_by_count":320},{"id":"1606.05336","title":"On the Expressive Power of Deep Neural Networks","created":"2016-06-16","cited_by_count":306},{"id":"2002.09277","title":"Kernel and Rich Regimes in Overparametrized Models","created":"2020-02-20","cited_by_count":306},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288},{"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":"1611.01491","title":"Understanding Deep Neural Networks with Rectified Linear Units","created":"2016-11-04","cited_by_count":257},{"id":"1806.00468","title":"Implicit Bias of Gradient Descent on Linear Convolutional Networks","created":"2018-06-01","cited_by_count":251},{"id":"2003.02218","title":"The large learning rate phase of deep learning: the catapult mechanism","created":"2020-03-04","cited_by_count":216},{"id":"2011.14522","title":"Feature Learning in Infinite-Width Neural Networks","created":"2020-11-30","cited_by_count":190},{"id":"2010.15110","title":"Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel","created":"2020-10-28","cited_by_count":187},{"id":"1810.10531","title":"A mathematical theory of semantic development in deep neural networks","created":"2018-10-23","cited_by_count":186},{"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":"1901.09021","title":"Complexity of Linear Regions in Deep Networks","created":"2019-01-25","cited_by_count":167},{"id":"1711.02114","title":"Bounding and Counting Linear Regions of Deep Neural Networks","created":"2017-11-06","cited_by_count":161},{"id":"1906.00904","title":"Deep ReLU Networks Have Surprisingly Few Activation Patterns","created":"2019-06-03","cited_by_count":161},{"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":"2006.14548","title":"Tensor Programs II: Neural Tangent Kernel for Any Architecture","created":"2020-06-25","cited_by_count":143},{"id":"1904.13262","title":"Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks","created":"2019-04-30","cited_by_count":124},{"id":"2310.17813","title":"A Spectral Condition for Feature Learning","created":"2023-10-26","cited_by_count":109},{"id":"2310.06110","title":"Grokking as the Transition from Lazy to Rich Training Dynamics","created":"2023-10-09","cited_by_count":108},{"id":"1805.00915","title":"Trainability and Accuracy of Neural Networks: An Interacting Particle System Approach","created":"2018-05-02","cited_by_count":106},{"id":"2111.00034","title":"Neural Networks as Kernel Learners: The Silent Alignment Effect","created":"2021-10-29","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":"2012.04728","title":"Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics","created":"2020-12-08","cited_by_count":96},{"id":"1312.6098","title":"On the number of response regions of deep feed forward networks with piece-wise linear activations","created":"2013-12-20","cited_by_count":94},{"id":"1509.08101","title":"Representation Benefits of Deep Feedforward Networks","created":"2015-09-27","cited_by_count":86},{"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":"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":"2110.13905","title":"Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias","created":"2021-10-26","cited_by_count":83},{"id":"2311.18817","title":"Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking","created":"2023-11-30","cited_by_count":80},{"id":"2206.00939","title":"Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs","created":"2022-06-02","cited_by_count":76},{"id":"2007.06738","title":"Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy","created":"2020-07-13","cited_by_count":71},{"id":"2307.02129","title":"How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model","created":"2023-07-05","cited_by_count":71},{"id":"2102.09769","title":"On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent","created":"2021-02-19","cited_by_count":70},{"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":"1909.12051","title":"The Implicit Bias of Depth: How Incremental Learning Drives Generalization","created":"2019-09-26","cited_by_count":64},{"id":"1803.08367","title":"Gradient Descent Quantizes ReLU Network Features","created":"2018-03-22","cited_by_count":61},{"id":"1905.07325","title":"Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models","created":"2019-05-17","cited_by_count":53},{"id":"2105.02716","title":"Noether's Learning Dynamics: Role of Symmetry Breaking in Neural Networks","created":"2021-05-06","cited_by_count":50},{"id":"2310.03789","title":"Grokking as a First Order Phase Transition in Two Layer Networks","created":"2023-10-05","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":"2207.04036","title":"Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent","created":"2022-07-08","cited_by_count":39},{"id":"2306.04251","title":"Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks","created":"2023-06-07","cited_by_count":39},{"id":"2402.04980","title":"Asymptotics of feature learning in two-layer networks after one gradient-step","created":"2024-02-07","cited_by_count":38},{"id":"2207.10430","title":"The Neural Race Reduction: Dynamics of Abstraction in Gated Networks","created":"2022-07-21","cited_by_count":37},{"id":"2202.07626","title":"Random Feature Amplification: Feature Learning and Generalization in Neural Networks","created":"2022-02-15","cited_by_count":35},{"id":"2306.04815","title":"Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning","created":"2023-06-07","cited_by_count":31},{"id":"2307.12851","title":"Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization","created":"2023-07-24","cited_by_count":28},{"id":"2210.03820","title":"The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks","created":"2022-10-07","cited_by_count":25},{"id":"2202.04777","title":"Exact Solutions of a Deep Linear Network","created":"2022-02-10","cited_by_count":24},{"id":"2004.01025","title":"Mirrorless Mirror Descent: A Natural Derivation of Mirror Descent","created":"2020-04-02","cited_by_count":18},{"id":"2405.17580","title":"Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes","created":"2024-05-27","cited_by_count":18},{"id":"2305.12467","title":"Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks","created":"2023-05-21","cited_by_count":15},{"id":"2310.08513","title":"How connectivity structure shapes rich and lazy learning in neural circuits","created":"2023-10-12","cited_by_count":15},{"id":"1901.09085","title":"Generalisation dynamics of online learning in over-parameterised neural networks","created":"2019-01-25","cited_by_count":9},{"id":"2206.02139","title":"Early Stage Convergence and Global Convergence of Training Mildly Parameterized Neural Networks","created":"2022-06-05","cited_by_count":5}],"next_cursor":null}