{"list":"other","total":56,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"id":"2006.06676","title":"Training Generative Adversarial Networks with Limited Data","created":"2020-06-11","cited_by_count":1186},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1611.08097","title":"Geometric deep learning: going beyond Euclidean data","created":"2016-11-24","cited_by_count":1048},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"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":"1611.08402","title":"Geometric deep learning on graphs and manifolds using mixture model CNNs","created":"2016-11-25","cited_by_count":468},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"1805.09112","title":"Hyperbolic Neural Networks","created":"2018-05-23","cited_by_count":402},{"id":"1402.1869","title":"On the Number of Linear Regions of Deep Neural Networks","created":"2014-02-08","cited_by_count":381},{"id":"1707.09564","title":"A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks","created":"2017-07-29","cited_by_count":314},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"1606.05336","title":"On the Expressive Power of Deep Neural Networks","created":"2016-06-16","cited_by_count":306},{"id":"1706.04454","title":"Empirical Analysis of the Hessian of Over-Parametrized Neural Networks","created":"2017-06-14","cited_by_count":290},{"id":"1606.05340","title":"Exponential expressivity in deep neural networks through transient chaos","created":"2016-06-16","cited_by_count":261},{"id":"1506.05163","title":"Deep Convolutional Networks on Graph-Structured Data","created":"2015-06-16","cited_by_count":246},{"id":"1503.01243","title":"A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights","created":"2015-03-04","cited_by_count":206},{"id":"1802.08760","title":"Sensitivity and Generalization in Neural Networks: an Empirical Study","created":"2018-02-23","cited_by_count":189},{"id":"1412.6544","title":"Qualitatively characterizing neural network optimization problems","created":"2014-12-19","cited_by_count":188},{"id":"1810.02281","title":"A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks","created":"2018-10-04","cited_by_count":184},{"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":"1710.05468","title":"Generalization in Deep Learning","created":"2017-10-16","cited_by_count":146},{"id":"1710.06451","title":"A Bayesian Perspective on Generalization and Stochastic Gradient Descent","created":"2017-10-17","cited_by_count":135},{"id":"2003.13913","title":"Flows for simultaneous manifold learning and density estimation","created":"2020-03-31","cited_by_count":118},{"id":"1909.05989","title":"Finite Depth and Width Corrections to the Neural Tangent Kernel","created":"2019-09-13","cited_by_count":115},{"id":"1708.02691","title":"Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations","created":"2017-08-09","cited_by_count":104},{"id":"1711.01530","title":"Fisher-Rao Metric, Geometry, and Complexity of Neural Networks","created":"2017-11-05","cited_by_count":100},{"id":"2006.08195","title":"Neural Networks Fail to Learn Periodic Functions and How to Fix It","created":"2020-06-15","cited_by_count":100},{"id":"2012.04728","title":"Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics","created":"2020-12-08","cited_by_count":96},{"id":"1509.08101","title":"Representation Benefits of Deep Feedforward Networks","created":"2015-09-27","cited_by_count":86},{"id":"1908.00695","title":"Deep ReLU network approximation of functions on a manifold","created":"2019-08-02","cited_by_count":74},{"id":"1608.03287","title":"Deep vs. shallow networks : An approximation theory perspective","created":"2016-08-10","cited_by_count":63},{"id":"1509.07385","title":"Provable approximation properties for deep neural networks","created":"2015-09-24","cited_by_count":60},{"id":"1812.05994","title":"Products of Many Large Random Matrices and Gradients in Deep Neural Networks","created":"2018-12-14","cited_by_count":49},{"id":"2008.11245","title":"Deep Networks and the Multiple Manifold Problem","created":"2020-08-25","cited_by_count":35},{"id":"2007.11471","title":"Geometric compression of invariant manifolds in neural nets","created":"2020-07-22","cited_by_count":28},{"id":"1305.7255","title":"Non-linear dimensionality reduction: Riemannian metric estimation and the problem of geometric discovery","created":"2013-05-30","cited_by_count":14},{"id":"1909.11500","title":"Modelling the influence of data structure on learning in neural networks: the hidden manifold model","created":"2019-09-25","cited_by_count":13},{"id":"2008.02545","title":"A deep network construction that adapts to intrinsic dimensionality beyond the domain","created":"2020-08-06","cited_by_count":10},{"id":"2107.14324","title":"Deep Networks Provably Classify Data on Curves","created":"2021-07-29","cited_by_count":6}],"next_cursor":null}