{"list":"other","total":83,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"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":"1511.04599","title":"DeepFool: a simple and accurate method to fool deep neural networks","created":"2015-11-14","cited_by_count":1318},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"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":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"1509.01240","title":"Train faster, generalize better: Stability of stochastic gradient descent","created":"2015-09-03","cited_by_count":552},{"id":"1602.07868","title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","created":"2016-02-25","cited_by_count":543},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1701.06548","title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","created":"2017-01-23","cited_by_count":464},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"1803.00885","title":"Essentially No Barriers in Neural Network Energy Landscape","created":"2018-03-02","cited_by_count":330},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293},{"id":"1901.10159","title":"An Investigation into Neural Net Optimization via Hessian Eigenvalue Density","created":"2019-01-29","cited_by_count":292},{"id":"1706.04454","title":"Empirical Analysis of the Hessian of Over-Parametrized Neural Networks","created":"2017-06-14","cited_by_count":290},{"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":"1705.08292","title":"The Marginal Value of Adaptive Gradient Methods in Machine Learning","created":"2017-05-23","cited_by_count":250},{"id":"1503.02101","title":"Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition","created":"2015-03-06","cited_by_count":243},{"id":"1605.07110","title":"Deep Learning without Poor Local Minima","created":"2016-05-23","cited_by_count":234},{"id":"1901.06053","title":"A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks","created":"2019-01-18","cited_by_count":214},{"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":"1902.09843","title":"Adaptive Gradient Methods with Dynamic Bound of Learning Rate","created":"2019-02-26","cited_by_count":183},{"id":"2006.06914","title":"Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses","created":"2020-06-12","cited_by_count":173},{"id":"1610.02915","title":"Deep Pyramidal Residual Networks","created":"2016-10-10","cited_by_count":163},{"id":"1412.7525","title":"Difference Target Propagation","created":"2014-12-23","cited_by_count":148},{"id":"1705.09886","title":"Convergence Analysis of Two-layer Neural Networks with ReLU Activation","created":"2017-05-28","cited_by_count":137},{"id":"1704.00708","title":"No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis","created":"2017-04-03","cited_by_count":129},{"id":"1506.02617","title":"Path-SGD: Path-Normalized Optimization in Deep Neural Networks","created":"2015-06-08","cited_by_count":120},{"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":"1803.01206","title":"On the Power of Over-parametrization in Neural Networks with Quadratic Activation","created":"2018-03-03","cited_by_count":102},{"id":"1807.04587","title":"Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures","created":"2018-07-12","cited_by_count":101},{"id":"1711.01530","title":"Fisher-Rao Metric, Geometry, and Complexity of Neural Networks","created":"2017-11-05","cited_by_count":100},{"id":"1706.03175","title":"Recovery Guarantees for One-hidden-layer Neural Networks","created":"2017-06-10","cited_by_count":94},{"id":"1710.10174","title":"SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data","created":"2017-10-27","cited_by_count":79},{"id":"2010.11924","title":"In Search of Robust Measures of Generalization","created":"2020-10-22","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":"1605.02026","title":"Training Neural Networks Without Gradients: A Scalable ADMM Approach","created":"2016-05-06","cited_by_count":61},{"id":"1702.07966","title":"Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs","created":"2017-02-26","cited_by_count":61},{"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":"1507.00210","title":"Natural Neural Networks","created":"2015-07-01","cited_by_count":44},{"id":"1610.04574","title":"Generalization Error of Invariant Classifiers","created":"2016-10-14","cited_by_count":42},{"id":"1509.05753","title":"Subdominant Dense Clusters Allow for Simple Learning and High Computational Performance in Neural Networks with Discrete Synapses","created":"2015-09-18","cited_by_count":39},{"id":"1603.09025","title":"Recurrent Batch Normalization","created":"2016-03-30","cited_by_count":36},{"id":"1910.01671","title":"Pure and Spurious Critical Points: a Geometric Study of Linear Networks","created":"2019-10-03","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":"2006.05720","title":"Extrapolation for Large-batch Training in Deep Learning","created":"2020-06-10","cited_by_count":25},{"id":"1602.05908","title":"Efficient approaches for escaping higher order saddle points in non-convex optimization","created":"2016-02-18","cited_by_count":23},{"id":"1806.09077","title":"Beyond Backprop: Online Alternating Minimization with Auxiliary Variables","created":"2018-06-24","cited_by_count":23},{"id":"1506.07540","title":"Global Optimality in Tensor Factorization, Deep Learning, and Beyond","created":"2015-06-24","cited_by_count":22},{"id":"1511.04210","title":"On the Quality of the Initial Basin in Overspecified Neural Networks","created":"2015-11-13","cited_by_count":20},{"id":"1805.01532","title":"Lifted Neural Networks","created":"2018-05-03","cited_by_count":20},{"id":"1803.09082","title":"A Proximal Block Coordinate Descent Algorithm for Deep Neural Network Training","created":"2018-03-24","cited_by_count":15},{"id":"1712.04741","title":"Mathematics of Deep Learning","created":"2017-12-13","cited_by_count":11},{"id":"1608.04980","title":"Mollifying Networks","created":"2016-08-17","cited_by_count":10},{"id":"1601.04114","title":"Training Recurrent Neural Networks by Diffusion","created":"2016-01-16","cited_by_count":9},{"id":"1905.11286","title":"Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks","created":"2019-05-27","cited_by_count":9},{"id":"1802.06875","title":"LSALSA: Accelerated Source Separation via Learned Sparse Coding","created":"2018-02-13","cited_by_count":7},{"id":"1906.10822","title":"Gradient Noise Convolution (GNC): Smoothing Loss Function for Distributed Large-Batch SGD","created":"2019-06-26","cited_by_count":7},{"id":"1602.04129","title":"Learning may need only a few bits of synaptic precision","created":"2016-02-12","cited_by_count":5},{"id":"2001.01678","title":"How neural networks find generalizable solutions: Self-tuned annealing in deep learning","created":"2020-01-06","cited_by_count":5},{"id":"1511.06485","title":"On the energy landscape of deep networks","created":"2015-11-20","cited_by_count":3},{"id":"1702.03380","title":"Training Deep Neural Networks via Optimization Over Graphs","created":"2017-02-11","cited_by_count":1},{"id":"1808.01352","title":"DeepCloak: Adversarial Crafting As a Defensive Measure to Cloak Processes","created":"2018-08-03","cited_by_count":1}],"next_cursor":null}