{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"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":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"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":"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":"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":"1611.01540","title":"Topology and Geometry of Half-Rectified Network Optimization","created":"2016-11-04","cited_by_count":102},{"id":"1412.6651","title":"Deep learning with Elastic Averaging SGD","created":"2014-12-20","cited_by_count":90},{"id":"1806.10909","title":"ResNet with one-neuron hidden layers is a Universal Approximator","created":"2018-06-28","cited_by_count":79},{"id":"1704.08045","title":"The loss surface of deep and wide neural networks","created":"2017-04-26","cited_by_count":74},{"id":"1702.07966","title":"Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs","created":"2017-02-26","cited_by_count":61},{"id":"1706.05507","title":"Variants of RMSProp and Adagrad with Logarithmic Regret Bounds","created":"2017-06-17","cited_by_count":50},{"id":"1908.03673","title":"Recent Advances in Deep Learning for Object Detection","created":"2019-08-10","cited_by_count":50},{"id":"1906.05661","title":"Training Neural Networks for and by Interpolation","created":"2019-06-13","cited_by_count":45},{"id":"1703.02628","title":"Global optimization of Lipschitz functions","created":"2017-03-07","cited_by_count":39},{"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":"1705.07576","title":"Global Guarantees for Enforcing Deep Generative Priors by Empirical Risk","created":"2017-05-22","cited_by_count":37},{"id":"1412.4564","title":"MatConvNet - Convolutional Neural Networks for MATLAB","created":"2014-12-15","cited_by_count":36},{"id":"1605.00405","title":"Gradient Descent Only Converges to Minimizers: Non-Isolated Critical Points and Invariant Regions","created":"2016-05-02","cited_by_count":34},{"id":"2101.07422","title":"SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images","created":"2021-01-19","cited_by_count":33},{"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":"1711.07354","title":"Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks","created":"2017-11-20","cited_by_count":26},{"id":"1805.08671","title":"Adding One Neuron Can Eliminate All Bad Local Minima","created":"2018-05-22","cited_by_count":21},{"id":"2011.00768","title":"Deep Feature Augmentation for Occluded Image Classification","created":"2020-11-02","cited_by_count":21},{"id":"1912.04514","title":"MDFN: Multi-Scale Deep Feature Learning Network for Object Detection","created":"2019-12-10","cited_by_count":19},{"id":"1811.07591","title":"Deep Frank-Wolfe For Neural Network Optimization","created":"2018-11-19","cited_by_count":11},{"id":"1711.06959","title":"BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning","created":"2017-11-19","cited_by_count":5},{"id":"1908.10012","title":"Unsupervised Deep Feature Transfer for Low Resolution Image Classification","created":"2019-08-27","cited_by_count":5},{"id":"2001.01275","title":"Self-Orthogonality Module: A Network Architecture Plug-in for Learning Orthogonal Filters","created":"2020-01-05","cited_by_count":5},{"id":"1611.01505","title":"Eve: A Gradient Based Optimization Method with Locally and Globally Adaptive Learning Rates","created":"2016-11-04","cited_by_count":1}],"next_cursor":null}