{"list":"other","total":52,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"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":"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":"1505.00853","title":"Empirical Evaluation of Rectified Activations in Convolutional Network","created":"2015-05-05","cited_by_count":519},{"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":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"2003.00307","title":"Loss landscapes and optimization in over-parameterized non-linear systems and neural networks","created":"2020-02-29","cited_by_count":233},{"id":"1808.00387","title":"Just Interpolate: Kernel \"Ridgeless\" Regression Can Generalize","created":"2018-08-01","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":"1811.08888","title":"Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks","created":"2018-11-21","cited_by_count":141},{"id":"1705.09886","title":"Convergence Analysis of Two-layer Neural Networks with ReLU Activation","created":"2017-05-28","cited_by_count":137},{"id":"2010.01092","title":"On the linearity of large non-linear models: when and why the tangent kernel is constant","created":"2020-10-02","cited_by_count":129},{"id":"1909.12292","title":"Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks","created":"2019-09-26","cited_by_count":121},{"id":"1805.00915","title":"Trainability and Accuracy of Neural Networks: An Interacting Particle System Approach","created":"2018-05-02","cited_by_count":106},{"id":"1712.08968","title":"Spurious Local Minima are Common in Two-Layer ReLU Neural Networks","created":"2017-12-24","cited_by_count":104},{"id":"1803.01206","title":"On the Power of Over-parametrization in Neural Networks with Quadratic Activation","created":"2018-03-03","cited_by_count":102},{"id":"1806.09471","title":"Does data interpolation contradict statistical optimality?","created":"2018-06-25","cited_by_count":95},{"id":"1911.00809","title":"Enhanced Convolutional Neural Tangent Kernels","created":"2019-11-03","cited_by_count":76},{"id":"1704.08045","title":"The loss surface of deep and wide neural networks","created":"2017-04-26","cited_by_count":74},{"id":"2001.05992","title":"Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks","created":"2020-01-16","cited_by_count":73},{"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":"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":"1702.07966","title":"Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs","created":"2017-02-26","cited_by_count":61},{"id":"1902.01384","title":"Generalization Error Bounds of Gradient Descent for Learning Over-parameterized Deep ReLU Networks","created":"2019-02-04","cited_by_count":60},{"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":"1906.03593","title":"Quadratic Suffices for Over-parametrization via Matrix Chernoff Bound","created":"2019-06-09","cited_by_count":59},{"id":"1705.04591","title":"Learning ReLUs via Gradient Descent","created":"2017-05-10","cited_by_count":54},{"id":"1712.05438","title":"Stochastic Particle Gradient Descent for Infinite Ensembles","created":"2017-12-14","cited_by_count":52},{"id":"1806.07808","title":"Learning One-hidden-layer ReLU Networks via Gradient Descent","created":"2018-06-20","cited_by_count":50},{"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":"1712.00779","title":"Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima","created":"2017-12-03","cited_by_count":40},{"id":"2002.06668","title":"Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality","created":"2020-02-16","cited_by_count":36},{"id":"2102.07346","title":"On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers","created":"2021-02-15","cited_by_count":35},{"id":"1611.03131","title":"Diverse Neural Network Learns True Target Functions","created":"2016-11-09","cited_by_count":33},{"id":"1908.02419","title":"Gradient Descent Finds Global Minima for Generalizable Deep Neural Networks of Practical Sizes","created":"2019-08-05","cited_by_count":29},{"id":"1902.07111","title":"Global Convergence of Adaptive Gradient Methods for An Over-parameterized Neural Network","created":"2019-02-19","cited_by_count":27},{"id":"1709.06129","title":"When is a Convolutional Filter Easy To Learn?","created":"2017-09-18","cited_by_count":21},{"id":"1802.06384","title":"Spurious Valleys in Two-layer Neural Network Optimization Landscapes","created":"2018-02-18","cited_by_count":21},{"id":"2010.12711","title":"On Convergence and Generalization of Dropout Training","created":"2020-10-23","cited_by_count":19},{"id":"1711.03440","title":"Learning Non-overlapping Convolutional Neural Networks with Multiple Kernels","created":"2017-11-08","cited_by_count":14},{"id":"1711.09090","title":"Invariance of Weight Distributions in Rectified MLPs","created":"2017-11-24","cited_by_count":12},{"id":"2112.02668","title":"On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons","created":"2021-12-05","cited_by_count":11},{"id":"1710.11205","title":"Critical Points of Neural Networks: Analytical Forms and Landscape Properties","created":"2017-10-30","cited_by_count":7},{"id":"2002.04026","title":"A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks","created":"2020-02-10","cited_by_count":5},{"id":"2101.04243","title":"A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks","created":"2021-01-12","cited_by_count":4},{"id":"1710.11241","title":"Theoretical properties of the global optimizer of two layer neural network","created":"2017-10-30","cited_by_count":3},{"id":"1911.05402","title":"Quadratic number of nodes is sufficient to learn a dataset via gradient descent","created":"2019-11-13","cited_by_count":1}],"next_cursor":null}