{"list":"other","total":59,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"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":"1812.07956","title":"On Lazy Training in Differentiable Programming","created":"2018-12-19","cited_by_count":675},{"id":"1711.00165","title":"Deep Neural Networks as Gaussian Processes","created":"2017-11-01","cited_by_count":622},{"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":"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":"1804.11271","title":"Gaussian Process Behaviour in Wide Deep Neural Networks","created":"2018-04-30","cited_by_count":317},{"id":"1606.05340","title":"Exponential expressivity in deep neural networks through transient chaos","created":"2016-06-16","cited_by_count":261},{"id":"1710.03667","title":"High-dimensional dynamics of generalization error in neural networks","created":"2017-10-10","cited_by_count":241},{"id":"2003.02218","title":"The large learning rate phase of deep learning: the catapult mechanism","created":"2020-03-04","cited_by_count":216},{"id":"2002.02561","title":"Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks","created":"2020-02-07","cited_by_count":200},{"id":"1611.01232","title":"Deep Information Propagation","created":"2016-11-04","cited_by_count":195},{"id":"2011.14522","title":"Feature Learning in Infinite-Width Neural Networks","created":"2020-11-30","cited_by_count":190},{"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":"1810.02281","title":"A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks","created":"2018-10-04","cited_by_count":184},{"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":"2006.13198","title":"Spectral Bias and Task-Model Alignment Explain Generalization in Kernel Regression and Infinitely Wide Neural Networks","created":"2020-06-23","cited_by_count":166},{"id":"1910.12478","title":"Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes","created":"2019-10-28","cited_by_count":151},{"id":"1902.04760","title":"Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation","created":"2019-02-13","cited_by_count":149},{"id":"2006.14548","title":"Tensor Programs II: Neural Tangent Kernel for Any Architecture","created":"2020-06-25","cited_by_count":143},{"id":"2102.08127","title":"Learning curves of generic features maps for realistic datasets with a teacher-student model","created":"2021-02-16","cited_by_count":126},{"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":"1909.08156","title":"Dynamics of Deep Neural Networks and Neural Tangent Hierarchy","created":"2019-09-18","cited_by_count":96},{"id":"1712.08969","title":"Mean Field Residual Networks: On the Edge of Chaos","created":"2017-12-24","cited_by_count":83},{"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":"2012.04030","title":"Statistical Mechanics of Deep Linear Neural Networks: The Back-Propagating Kernel Renormalization","created":"2020-12-07","cited_by_count":71},{"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":"2006.06098","title":"Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification","created":"2020-06-10","cited_by_count":60},{"id":"2105.03703","title":"Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics","created":"2021-05-08","cited_by_count":57},{"id":"2006.09796","title":"Kernel Alignment Risk Estimator: Risk Prediction from Training Data","created":"2020-06-17","cited_by_count":54},{"id":"2112.15383","title":"Separation of Scales and a Thermodynamic Description of Feature Learning in Some CNNs","created":"2021-12-31","cited_by_count":53},{"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":"1910.08013","title":"Why bigger is not always better: on finite and infinite neural networks","created":"2019-10-17","cited_by_count":41},{"id":"2006.08643","title":"On the training dynamics of deep networks with $L_2$ regularization","created":"2020-06-15","cited_by_count":39},{"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":"2004.01190","title":"Predicting the outputs of finite deep neural networks trained with noisy gradients","created":"2020-04-02","cited_by_count":31},{"id":"1902.00139","title":"Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models","created":"2019-02-01","cited_by_count":28},{"id":"2002.12493","title":"Optimization with Momentum: Dynamical, Control-Theoretic, and Symplectic Perspectives","created":"2020-02-28","cited_by_count":27},{"id":"2110.03922","title":"The Eigenlearning Framework: A Conservation Law Perspective on Kernel Regression and Wide Neural Networks","created":"2021-10-08","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":"2105.14301","title":"A Theory of Neural Tangent Kernel Alignment and Its Influence on Training","created":"2021-05-29","cited_by_count":25},{"id":"2112.10852","title":"The effective noise of Stochastic Gradient Descent","created":"2021-12-20","cited_by_count":25},{"id":"1812.09066","title":"Marvels and Pitfalls of the Langevin Algorithm in Noisy High-dimensional Inference","created":"2018-12-21","cited_by_count":24},{"id":"2203.00573","title":"Contrasting random and learned features in deep Bayesian linear regression","created":"2022-03-01","cited_by_count":24},{"id":"2103.04902","title":"Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem","created":"2021-03-08","cited_by_count":23},{"id":"2112.05589","title":"Unified field theoretical approach to deep and recurrent neuronal networks","created":"2021-12-10","cited_by_count":20},{"id":"2110.11749","title":"Feature Learning and Signal Propagation in Deep Neural Networks","created":"2021-10-22","cited_by_count":18},{"id":"2008.08675","title":"Asymptotics of Wide Convolutional Neural Networks","created":"2020-08-19","cited_by_count":16},{"id":"2111.11954","title":"Depth induces scale-averaging in overparameterized linear Bayesian neural networks","created":"2021-11-23","cited_by_count":7},{"id":"2202.04509","title":"Optimal learning rate schedules in high-dimensional non-convex optimization problems","created":"2022-02-09","cited_by_count":4}],"next_cursor":null}