{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"id":"1509.01240","title":"Train faster, generalize better: Stability of stochastic gradient descent","created":"2015-09-03","cited_by_count":552},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"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":"1912.02365","title":"Lower Bounds for Non-Convex Stochastic Optimization","created":"2019-12-05","cited_by_count":307},{"id":"1905.10018","title":"Momentum-Based Variance Reduction in Non-Convex SGD","created":"2019-05-24","cited_by_count":306},{"id":"1807.01695","title":"SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path Integrated Differential Estimator","created":"2018-07-04","cited_by_count":287},{"id":"1703.00887","title":"How to Escape Saddle Points Efficiently","created":"2017-03-02","cited_by_count":285},{"id":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","cited_by_count":273},{"id":"1503.02101","title":"Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition","created":"2015-03-06","cited_by_count":243},{"id":"1706.01905","title":"Parameter Space Noise for Exploration","created":"2017-06-06","cited_by_count":161},{"id":"1511.06807","title":"Adding Gradient Noise Improves Learning for Very Deep Networks","created":"2015-11-21","cited_by_count":145},{"id":"1605.07272","title":"Matrix Completion has No Spurious Local Minimum","created":"2016-05-24","cited_by_count":125},{"id":"1802.06175","title":"An Alternative View: When Does SGD Escape Local Minima?","created":"2018-02-17","cited_by_count":115},{"id":"1707.05947","title":"Generalization Bounds of SGLD for Non-convex Learning: Two Theoretical Viewpoints","created":"2017-07-19","cited_by_count":82},{"id":"1907.04232","title":"Unified Optimal Analysis of the (Stochastic) Gradient Method","created":"2019-07-09","cited_by_count":82},{"id":"1310.3787","title":"Accelerated Gradient Methods for Nonconvex Nonlinear and Stochastic Programming","created":"2013-10-14","cited_by_count":75},{"id":"1702.05575","title":"A Hitting Time Analysis of Stochastic Gradient Langevin Dynamics","created":"2017-02-18","cited_by_count":71},{"id":"1711.10456","title":"Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent","created":"2017-11-28","cited_by_count":66},{"id":"1803.05999","title":"Escaping Saddles with Stochastic Gradients","created":"2018-03-15","cited_by_count":66},{"id":"1706.09156","title":"Non-convex Finite-Sum Optimization Via SCSG Methods","created":"2017-06-28","cited_by_count":61},{"id":"1801.02982","title":"How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD","created":"2018-01-08","cited_by_count":57},{"id":"1711.02838","title":"Stochastic Cubic Regularization for Fast Nonconvex Optimization","created":"2017-11-08","cited_by_count":55},{"id":"1708.08694","title":"Natasha 2: Faster Non-Convex Optimization Than SGD","created":"2017-08-29","cited_by_count":49},{"id":"1812.04529","title":"On the Ineffectiveness of Variance Reduced Optimization for Deep Learning","created":"2018-12-11","cited_by_count":48},{"id":"1705.02766","title":"\"Convex Until Proven Guilty\": Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions","created":"2017-05-08","cited_by_count":46},{"id":"1708.07164","title":"Newton-Type Methods for Non-Convex Optimization Under Inexact Hessian Information","created":"2017-08-23","cited_by_count":41},{"id":"1902.00247","title":"Sharp Analysis for Nonconvex SGD Escaping from Saddle Points","created":"2019-02-01","cited_by_count":40},{"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":"1711.06673","title":"Neon2: Finding Local Minima via First-Order Oracles","created":"2017-11-17","cited_by_count":36},{"id":"1906.11985","title":"Near-Optimal Methods for Minimizing Star-Convex Functions and Beyond","created":"2019-06-27","cited_by_count":36},{"id":"1503.03712","title":"On Graduated Optimization for Stochastic Non-Convex Problems","created":"2015-03-12","cited_by_count":34},{"id":"1711.01944","title":"First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time","created":"2017-11-03","cited_by_count":29},{"id":"1805.07898","title":"SmoothOut: Smoothing Out Sharp Minima to Improve Generalization in Deep Learning","created":"2018-05-21","cited_by_count":25},{"id":"1904.09265","title":"SSRGD: Simple Stochastic Recursive Gradient Descent for Escaping Saddle Points","created":"2019-04-19","cited_by_count":25},{"id":"2006.05720","title":"Extrapolation for Large-batch Training in Deep Learning","created":"2020-06-10","cited_by_count":25},{"id":"1611.00756","title":"Accelerated Methods for Non-Convex Optimization","created":"2016-11-02","cited_by_count":20},{"id":"1709.01434","title":"A Generic Approach for Escaping Saddle points","created":"2017-09-05","cited_by_count":13},{"id":"1803.09357","title":"On the Local Minima of the Empirical Risk","created":"2018-03-25","cited_by_count":12},{"id":"1501.07242","title":"Escaping the Local Minima via Simulated Annealing: Optimization of Approximately Convex Functions","created":"2015-01-28","cited_by_count":10},{"id":"1511.04466","title":"Optimizing Star-Convex Functions","created":"2015-11-13","cited_by_count":9},{"id":"1712.01033","title":"NEON+: Accelerated Gradient Methods for Extracting Negative Curvature for Non-Convex Optimization","created":"2017-12-04","cited_by_count":9},{"id":"2010.04937","title":"On The Convergence of First Order Methods for Quasar-Convex Optimization","created":"2020-10-10","cited_by_count":8},{"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":"1707.02727","title":"Stochastic Variance Reduction Gradient for a Non-convex Problem Using Graduated Optimization","created":"2017-07-10","cited_by_count":1}],"next_cursor":null}