{"list":"other","total":51,"rows":[{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"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":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"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":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"1803.00885","title":"Essentially No Barriers in Neural Network Energy Landscape","created":"2018-03-02","cited_by_count":330},{"id":"1705.09280","title":"Implicit Regularization in Matrix Factorization","created":"2017-05-25","cited_by_count":322},{"id":"1906.05890","title":"Gradient Descent Maximizes the Margin of Homogeneous Neural Networks","created":"2019-06-13","cited_by_count":320},{"id":"2002.09277","title":"Kernel and Rich Regimes in Overparametrized Models","created":"2020-02-20","cited_by_count":306},{"id":"1802.06509","title":"On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization","created":"2018-02-19","cited_by_count":284},{"id":"1705.08741","title":"Train longer, generalize better: closing the generalization gap in large batch training of neural networks","created":"2017-05-24","cited_by_count":279},{"id":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","cited_by_count":273},{"id":"1802.08246","title":"Characterizing Implicit Bias in Terms of Optimization Geometry","created":"2018-02-22","cited_by_count":266},{"id":"1404.5997","title":"One weird trick for parallelizing convolutional neural networks","created":"2014-04-23","cited_by_count":264},{"id":"1808.01204","title":"Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data","created":"2018-08-03","cited_by_count":261},{"id":"2101.12176","title":"On the Origin of Implicit Regularization in Stochastic Gradient Descent","created":"2021-01-28","cited_by_count":184},{"id":"1907.04595","title":"Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks","created":"2019-07-10","cited_by_count":162},{"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":"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":"1511.06251","title":"Stochastic modified equations and adaptive stochastic gradient algorithms","created":"2015-11-19","cited_by_count":142},{"id":"1904.09080","title":"Implicit regularization for deep neural networks driven by an Ornstein-Uhlenbeck like process","created":"2019-04-19","cited_by_count":123},{"id":"2106.06530","title":"Label Noise SGD Provably Prefers Flat Global Minimizers","created":"2021-06-11","cited_by_count":121},{"id":"1811.01558","title":"Stochastic Modified Equations and Dynamics of Stochastic Gradient Algorithms I: Mathematical Foundations","created":"2018-11-05","cited_by_count":114},{"id":"2106.09524","title":"Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity","created":"2021-06-17","cited_by_count":110},{"id":"1611.01540","title":"Topology and Geometry of Half-Rectified Network Optimization","created":"2016-11-04","cited_by_count":102},{"id":"2006.08680","title":"Shape Matters: Understanding the Implicit Bias of the Noise Covariance","created":"2020-06-15","cited_by_count":88},{"id":"1909.05122","title":"Implicit Regularization for Optimal Sparse Recovery","created":"2019-09-11","cited_by_count":80},{"id":"2102.12470","title":"On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)","created":"2021-02-24","cited_by_count":73},{"id":"2102.09769","title":"On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent","created":"2021-02-19","cited_by_count":70},{"id":"1904.01517","title":"Convergence rates for the stochastic gradient descent method for non-convex objective functions","created":"2019-04-02","cited_by_count":66},{"id":"1906.06247","title":"Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets","created":"2019-06-14","cited_by_count":63},{"id":"2010.02916","title":"Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate","created":"2020-10-06","cited_by_count":59},{"id":"1902.00621","title":"On Generalization Error Bounds of Noisy Gradient Methods for Non-Convex Learning","created":"2019-02-02","cited_by_count":57},{"id":"1702.08503","title":"SGD Learns the Conjugate Kernel Class of the Network","created":"2017-02-27","cited_by_count":54},{"id":"1901.07417","title":"On Connected Sublevel Sets in Deep Learning","created":"2019-01-22","cited_by_count":51},{"id":"1804.10200","title":"The loss landscape of overparameterized neural networks","created":"2018-04-26","cited_by_count":39},{"id":"1809.10749","title":"On the loss landscape of a class of deep neural networks with no bad local valleys","created":"2018-09-27","cited_by_count":38},{"id":"2010.08515","title":"Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets?","created":"2020-10-16","cited_by_count":34},{"id":"1803.00909","title":"Understanding the Loss Surface of Neural Networks for Binary Classification","created":"2018-02-19","cited_by_count":27},{"id":"2106.02588","title":"Stochastic gradient descent with noise of machine learning type. Part II: Continuous time analysis","created":"2021-06-04","cited_by_count":25},{"id":"1802.06384","title":"Spurious Valleys in Two-layer Neural Network Optimization Landscapes","created":"2018-02-18","cited_by_count":21},{"id":"1710.07406","title":"First-order Methods Almost Always Avoid Saddle Points","created":"2017-10-20","cited_by_count":14},{"id":"2002.03495","title":"A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat Minima","created":"2020-02-10","cited_by_count":11},{"id":"2005.04210","title":"The critical locus of overparameterized neural networks","created":"2020-05-08","cited_by_count":6}],"next_cursor":null}