{"list":"other","total":94,"rows":[{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"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":"1812.07956","title":"On Lazy Training in Differentiable Programming","created":"2018-12-19","cited_by_count":675},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"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":"1906.11300","title":"Benign Overfitting in Linear Regression","created":"2019-06-26","cited_by_count":549},{"id":"1903.08560","title":"Surprises in High-Dimensional Ridgeless Least Squares Interpolation","created":"2019-03-19","cited_by_count":513},{"id":"1708.06633","title":"Nonparametric regression using deep neural networks with ReLU activation function","created":"2017-08-22","cited_by_count":433},{"id":"1908.05355","title":"The generalization error of random features regression: Precise asymptotics and double descent curve","created":"2019-08-14","cited_by_count":413},{"id":"2002.09277","title":"Kernel and Rich Regimes in Overparametrized Models","created":"2020-02-20","cited_by_count":306},{"id":"2103.09177","title":"Deep learning: a statistical viewpoint","created":"2021-03-16","cited_by_count":240},{"id":"2002.02561","title":"Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks","created":"2020-02-07","cited_by_count":200},{"id":"1808.00387","title":"Just Interpolate: Kernel \"Ridgeless\" Regression Can Generalize","created":"2018-08-01","cited_by_count":190},{"id":"2011.14522","title":"Feature Learning in Infinite-Width Neural Networks","created":"2020-11-30","cited_by_count":190},{"id":"1802.01396","title":"To understand deep learning we need to understand kernel learning","created":"2018-02-05","cited_by_count":187},{"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":"1810.08033","title":"Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality","created":"2018-10-18","cited_by_count":162},{"id":"2206.15144","title":"Neural Networks can Learn Representations with Gradient Descent","created":"2022-06-30","cited_by_count":161},{"id":"1904.12191","title":"Linearized two-layers neural networks in high dimension","created":"2019-04-27","cited_by_count":155},{"id":"2009.14286","title":"Benign overfitting in ridge regression","created":"2020-09-29","cited_by_count":153},{"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":"2302.11055","title":"SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics","created":"2023-02-21","cited_by_count":143},{"id":"2202.08658","title":"The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks","created":"2022-02-17","cited_by_count":142},{"id":"2105.14368","title":"Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation","created":"2021-05-29","cited_by_count":132},{"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":"2002.09339","title":"Generalisation error in learning with random features and the hidden manifold model","created":"2020-02-21","cited_by_count":127},{"id":"2003.10409","title":"Online stochastic gradient descent on non-convex losses from high-dimensional inference","created":"2020-03-23","cited_by_count":119},{"id":"1909.05989","title":"Finite Depth and Width Corrections to the Neural Tangent Kernel","created":"2019-09-13","cited_by_count":115},{"id":"1702.07254","title":"Sobolev Norm Learning Rates for Regularized Least-Squares Algorithm","created":"2017-02-23","cited_by_count":114},{"id":"2101.10588","title":"Generalization error of random features and kernel methods: hypercontractivity and kernel matrix concentration","created":"2021-01-26","cited_by_count":110},{"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":"1909.08156","title":"Dynamics of Deep Neural Networks and Neural Tangent Hierarchy","created":"2019-09-18","cited_by_count":96},{"id":"2105.15004","title":"Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime","created":"2021-05-31","cited_by_count":96},{"id":"2102.13219","title":"Learning with invariances in random features and kernel models","created":"2021-02-25","cited_by_count":89},{"id":"1906.08899","title":"Limitations of Lazy Training of Two-layers Neural Networks","created":"2019-06-21","cited_by_count":87},{"id":"2007.12826","title":"The Interpolation Phase Transition in Neural Networks: Memorization and Generalization under Lazy Training","created":"2020-07-25","cited_by_count":84},{"id":"1909.05122","title":"Implicit Regularization for Optimal Sparse Recovery","created":"2019-09-11","cited_by_count":80},{"id":"1910.00019","title":"Non-Gaussian processes and neural networks at finite widths","created":"2019-09-30","cited_by_count":78},{"id":"1909.11304","title":"Asymptotics of Wide Networks from Feynman Diagrams","created":"2019-09-25","cited_by_count":77},{"id":"1805.10074","title":"Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes","created":"2018-05-25","cited_by_count":69},{"id":"1604.04054","title":"Optimal Rates For Regularization Of Statistical Inverse Learning Problems","created":"2016-04-14","cited_by_count":68},{"id":"1906.05392","title":"Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian","created":"2019-06-12","cited_by_count":67},{"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":"1801.06720","title":"Optimal Rates for Spectral Algorithms with Least-Squares Regression over Hilbert Spaces","created":"2018-01-20","cited_by_count":59},{"id":"1805.10939","title":"Optimal ridge penalty for real-world high-dimensional data can be zero or negative due to the implicit ridge regularization","created":"2018-05-28","cited_by_count":53},{"id":"2106.06770","title":"What can linearized neural networks actually say about generalization?","created":"2021-06-12","cited_by_count":49},{"id":"2310.07891","title":"A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks","created":"2023-10-11","cited_by_count":49},{"id":"2204.10425","title":"Spectrum of inner-product kernel matrices in the polynomial regime and multiple descent phenomenon in kernel ridge regression","created":"2022-04-21","cited_by_count":45},{"id":"1812.11167","title":"Consistency of Interpolation with Laplace Kernels is a High-Dimensional Phenomenon","created":"2018-12-28","cited_by_count":44},{"id":"2304.03408","title":"Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks","created":"2023-04-06","cited_by_count":43},{"id":"2010.02681","title":"Kernel regression in high dimensions: Refined analysis beyond double descent","created":"2020-10-06","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":"2207.06569","title":"Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting","created":"2022-07-14","cited_by_count":36},{"id":"2006.12297","title":"Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime","created":"2020-06-22","cited_by_count":35},{"id":"2012.04477","title":"Analyzing Finite Neural Networks: Can We Trust Neural Tangent Kernel Theory?","created":"2020-12-08","cited_by_count":33},{"id":"2106.04110","title":"A self consistent theory of Gaussian Processes captures feature learning effects in finite CNNs","created":"2021-06-08","cited_by_count":33},{"id":"2104.04244","title":"How rotational invariance of common kernels prevents generalization in high dimensions","created":"2021-04-09","cited_by_count":32},{"id":"1904.05526","title":"A Selective Overview of Deep Learning","created":"2019-04-10","cited_by_count":31},{"id":"2305.02657","title":"On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains","created":"2023-05-04","cited_by_count":31},{"id":"2108.05574","title":"Implicit Sparse Regularization: The Impact of Depth and Early Stopping","created":"2021-08-12","cited_by_count":30},{"id":"2302.05933","title":"Generalization Ability of Wide Neural Networks on $\\mathbb{R}$","created":"2023-02-12","cited_by_count":30},{"id":"2303.14942","title":"On the Optimality of Misspecified Spectral Algorithms","created":"2023-03-27","cited_by_count":28},{"id":"2403.08938","title":"A non-asymptotic theory of Kernel Ridge Regression: deterministic equivalents, test error, and GCV estimator","created":"2024-03-13","cited_by_count":28},{"id":"2312.15995","title":"Generalization in Kernel Regression Under Realistic Assumptions","created":"2023-12-26","cited_by_count":27},{"id":"2305.14077","title":"Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension","created":"2023-05-23","cited_by_count":26},{"id":"1903.09367","title":"High-Dimensional Linear Regression via Implicit Regularization","created":"2019-03-22","cited_by_count":25},{"id":"2105.14301","title":"A Theory of Neural Tangent Kernel Alignment and Its Influence on Training","created":"2021-05-29","cited_by_count":25},{"id":"2212.13881","title":"Mechanism of feature learning in deep fully connected networks and kernel machines that recursively learn features","created":"2022-12-28","cited_by_count":25},{"id":"2208.13614","title":"Neural Tangent Kernel: A Survey","created":"2022-08-29","cited_by_count":23},{"id":"1801.07226","title":"Optimal Convergence for Distributed Learning with Stochastic Gradient Methods and Spectral Algorithms","created":"2018-01-22","cited_by_count":22},{"id":"2111.07167","title":"The Three Stages of Learning Dynamics in High-Dimensional Kernel Methods","created":"2021-11-13","cited_by_count":22},{"id":"2205.14846","title":"Precise Learning Curves and Higher-Order Scaling Limits for Dot Product Kernel Regression","created":"2022-05-30","cited_by_count":22},{"id":"2305.07241","title":"On the Optimality of Misspecified Kernel Ridge Regression","created":"2023-05-12","cited_by_count":20},{"id":"2401.07187","title":"A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models","created":"2024-01-14","cited_by_count":20},{"id":"2009.10008","title":"Kernel-Based Smoothness Analysis of Residual Networks","created":"2020-09-21","cited_by_count":19},{"id":"2205.06798","title":"Sharp Asymptotics of Kernel Ridge Regression Beyond the Linear Regime","created":"2022-05-13","cited_by_count":19},{"id":"2309.13337","title":"On the Asymptotic Learning Curves of Kernel Ridge Regression under Power-law Decay","created":"2023-09-23","cited_by_count":19},{"id":"2309.00570","title":"Mechanism of feature learning in convolutional neural networks","created":"2023-09-01","cited_by_count":17},{"id":"2303.15809","title":"Kernel interpolation generalizes poorly","created":"2023-03-28","cited_by_count":16},{"id":"2004.08436","title":"Analyzing the discrepancy principle for kernelized spectral filter learning algorithms","created":"2020-04-17","cited_by_count":15},{"id":"2205.13525","title":"On the Inconsistency of Kernel Ridgeless Regression in Fixed Dimensions","created":"2022-05-26","cited_by_count":13},{"id":"2402.01297","title":"Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum","created":"2024-02-02","cited_by_count":13},{"id":"2405.09362","title":"On the Saturation Effect of Kernel Ridge Regression","created":"2024-05-15","cited_by_count":13},{"id":"2309.04268","title":"Optimal Rate of Kernel Regression in Large Dimensions","created":"2023-09-08","cited_by_count":11},{"id":"2401.01270","title":"Optimal Rates of Kernel Ridge Regression under Source Condition in Large Dimensions","created":"2024-01-02","cited_by_count":11},{"id":"2401.01599","title":"Generalization Error Curves for Analytic Spectral Algorithms under Power-law Decay","created":"2024-01-03","cited_by_count":11},{"id":"2301.07605","title":"Strong inductive biases provably prevent harmless interpolation","created":"2023-01-18","cited_by_count":10},{"id":"2404.12597","title":"The phase diagram of kernel interpolation in large dimensions","created":"2024-04-19","cited_by_count":9},{"id":"2410.05626","title":"On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory","created":"2024-10-08","cited_by_count":5},{"id":"2409.00894","title":"Improving Adaptivity via Over-Parameterization in Sequence Models","created":"2024-09-02","cited_by_count":3}],"next_cursor":null}