{"list":"other","total":66,"rows":[{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"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":"1402.1869","title":"On the Number of Linear Regions of Deep Neural Networks","created":"2014-02-08","cited_by_count":381},{"id":"1803.00885","title":"Essentially No Barriers in Neural Network Energy Landscape","created":"2018-03-02","cited_by_count":330},{"id":"1406.2572","title":"Identifying and attacking the saddle point problem in high-dimensional non-convex optimization","created":"2014-06-10","cited_by_count":289},{"id":"1412.0233","title":"The Loss Surfaces of Multilayer Networks","created":"2014-11-30","cited_by_count":280},{"id":"1605.07110","title":"Deep Learning without Poor Local Minima","created":"2016-05-23","cited_by_count":234},{"id":"1412.6544","title":"Qualitatively characterizing neural network optimization problems","created":"2014-12-19","cited_by_count":188},{"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":"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":"1707.04926","title":"Theoretical insights into the optimization landscape of over-parameterized shallow neural networks","created":"2017-07-16","cited_by_count":128},{"id":"1605.07272","title":"Matrix Completion has No Spurious Local Minimum","created":"2016-05-24","cited_by_count":125},{"id":"1611.04231","title":"Identity Matters in Deep Learning","created":"2016-11-14","cited_by_count":109},{"id":"1712.08968","title":"Spurious Local Minima are Common in Two-Layer ReLU Neural Networks","created":"2017-12-24","cited_by_count":104},{"id":"1611.01540","title":"Topology and Geometry of Half-Rectified Network Optimization","created":"2016-11-04","cited_by_count":102},{"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":"1706.03175","title":"Recovery Guarantees for One-hidden-layer Neural Networks","created":"2017-06-10","cited_by_count":94},{"id":"1607.06534","title":"The Landscape of Empirical Risk for Non-convex Losses","created":"2016-07-22","cited_by_count":86},{"id":"1711.00501","title":"Learning One-hidden-layer Neural Networks with Landscape Design","created":"2017-11-01","cited_by_count":81},{"id":"1906.04724","title":"Large Scale Structure of Neural Network Loss Landscapes","created":"2019-06-11","cited_by_count":68},{"id":"1712.01473","title":"Deep linear neural networks with arbitrary loss: All local minima are global","created":"2017-12-05","cited_by_count":65},{"id":"2007.01429","title":"The Global Landscape of Neural Networks: An Overview","created":"2020-07-02","cited_by_count":57},{"id":"1703.00560","title":"An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis","created":"2017-03-02","cited_by_count":52},{"id":"1901.07417","title":"On Connected Sublevel Sets in Deep Learning","created":"2019-01-22","cited_by_count":51},{"id":"1806.07808","title":"Learning One-hidden-layer ReLU Networks via Gradient Descent","created":"2018-06-20","cited_by_count":50},{"id":"2006.00978","title":"On the Number of Linear Regions of Convolutional Neural Networks","created":"2020-06-01","cited_by_count":49},{"id":"2101.09612","title":"On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths","created":"2021-01-24","cited_by_count":44},{"id":"2012.10931","title":"Recent advances in deep learning theory","created":"2020-12-20","cited_by_count":41},{"id":"1901.00451","title":"SGD Converges to Global Minimum in Deep Learning via Star-convex Path","created":"2019-01-02","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":"1707.02444","title":"Global optimality conditions for deep neural networks","created":"2017-07-08","cited_by_count":31},{"id":"1605.08361","title":"No bad local minima: Data independent training error guarantees for multilayer neural networks","created":"2016-05-26","cited_by_count":30},{"id":"1702.08580","title":"Depth Creates No Bad Local Minima","created":"2017-02-27","cited_by_count":29},{"id":"1802.03487","title":"Small nonlinearities in activation functions create bad local minima in neural networks","created":"2018-02-10","cited_by_count":28},{"id":"1803.00909","title":"Understanding the Loss Surface of Neural Networks for Binary Classification","created":"2018-02-19","cited_by_count":27},{"id":"1802.06384","title":"Spurious Valleys in Two-layer Neural Network Optimization Landscapes","created":"2018-02-18","cited_by_count":21},{"id":"1805.08671","title":"Adding One Neuron Can Eliminate All Bad Local Minima","created":"2018-05-22","cited_by_count":21},{"id":"1910.00359","title":"Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory","created":"2019-10-01","cited_by_count":21},{"id":"1511.04210","title":"On the Quality of the Initial Basin in Overspecified Neural Networks","created":"2015-11-13","cited_by_count":20},{"id":"1611.06310","title":"Local minima in training of neural networks","created":"2016-11-19","cited_by_count":19},{"id":"1702.05777","title":"Exponentially vanishing sub-optimal local minima in multilayer neural networks","created":"2017-02-19","cited_by_count":19},{"id":"2003.12236","title":"Piecewise linear activations substantially shape the loss surfaces of neural networks","created":"2020-03-27","cited_by_count":19},{"id":"1810.09038","title":"Depth with Nonlinearity Creates No Bad Local Minima in ResNets","created":"2018-10-21","cited_by_count":17},{"id":"1812.11039","title":"On the Benefit of Width for Neural Networks: Disappearance of Bad Basins","created":"2018-12-28","cited_by_count":16},{"id":"1810.12805","title":"Piecewise Strong Convexity of Neural Networks","created":"2018-10-30","cited_by_count":13},{"id":"1804.06739","title":"Are ResNets Provably Better than Linear Predictors?","created":"2018-04-18","cited_by_count":12},{"id":"1803.02968","title":"Learning Deep Models: Critical Points and Local Openness","created":"2018-03-08","cited_by_count":10},{"id":"1901.00279","title":"Elimination of All Bad Local Minima in Deep Learning","created":"2019-01-02","cited_by_count":10},{"id":"1712.10132","title":"The Multilinear Structure of ReLU Networks","created":"2017-12-29","cited_by_count":9},{"id":"1710.11205","title":"Critical Points of Neural Networks: Analytical Forms and Landscape Properties","created":"2017-10-30","cited_by_count":7},{"id":"1810.04133","title":"Learning One-hidden-layer Neural Networks under General Input Distributions","created":"2018-10-09","cited_by_count":7},{"id":"1710.02196","title":"Porcupine Neural Networks: (Almost) All Local Optima are Global","created":"2017-10-05","cited_by_count":6},{"id":"1901.09827","title":"Depth creates no more spurious local minima","created":"2019-01-28","cited_by_count":5},{"id":"2008.00741","title":"Low-loss connection of weight vectors: distribution-based approaches","created":"2020-08-03","cited_by_count":3},{"id":"2001.00098","title":"Avoiding Spurious Local Minima in Deep Quadratic Networks","created":"2019-12-31","cited_by_count":2},{"id":"2009.08274","title":"Deforming the Loss Surface to Affect the Behaviour of the Optimizer","created":"2020-09-14","cited_by_count":1}],"next_cursor":null}