{"list":"other","total":52,"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"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":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"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":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"1412.1193","title":"New insights and perspectives on the natural gradient method","created":"2014-12-03","cited_by_count":443},{"id":"2103.00065","title":"Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability","created":"2021-02-26","cited_by_count":427},{"id":"1802.06509","title":"On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization","created":"2018-02-19","cited_by_count":284},{"id":"2102.06810","title":"Understanding self-supervised Learning Dynamics without Contrastive Pairs","created":"2021-02-12","cited_by_count":256},{"id":"1905.12558","title":"Limitations of the Empirical Fisher Approximation for Natural Gradient Descent","created":"2019-05-29","cited_by_count":217},{"id":"2003.02218","title":"The large learning rate phase of deep learning: the catapult mechanism","created":"2020-03-04","cited_by_count":216},{"id":"1503.01243","title":"A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights","created":"2015-03-04","cited_by_count":206},{"id":"2101.12176","title":"On the Origin of Implicit Regularization in Stochastic Gradient Descent","created":"2021-01-28","cited_by_count":184},{"id":"1806.00900","title":"Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced","created":"2018-06-04","cited_by_count":177},{"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":"1301.3584","title":"Revisiting Natural Gradient for Deep Networks","created":"2013-01-16","cited_by_count":159},{"id":"1806.02375","title":"Understanding Batch Normalization","created":"2018-06-01","cited_by_count":159},{"id":"2002.09572","title":"The Break-Even Point on Optimization Trajectories of Deep Neural Networks","created":"2020-02-21","cited_by_count":150},{"id":"2009.11162","title":"Implicit Gradient Regularization","created":"2020-09-23","cited_by_count":146},{"id":"1511.06251","title":"Stochastic modified equations and adaptive stochastic gradient algorithms","created":"2015-11-19","cited_by_count":142},{"id":"1602.01407","title":"A Kronecker-factored approximate Fisher matrix for convolution layers","created":"2016-02-03","cited_by_count":141},{"id":"1706.05350","title":"L2 Regularization versus Batch and Weight Normalization","created":"2017-06-16","cited_by_count":124},{"id":"1910.07454","title":"An Exponential Learning Rate Schedule for Deep Learning","created":"2019-10-16","cited_by_count":121},{"id":"1506.02617","title":"Path-SGD: Path-Normalized Optimization in Deep Neural Networks","created":"2015-06-08","cited_by_count":120},{"id":"2007.01547","title":"Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers","created":"2020-07-03","cited_by_count":119},{"id":"1810.12281","title":"Three Mechanisms of Weight Decay Regularization","created":"2018-10-29","cited_by_count":113},{"id":"1603.04245","title":"A Variational Perspective on Accelerated Methods in Optimization","created":"2016-03-14","cited_by_count":110},{"id":"1910.05446","title":"On Empirical Comparisons of Optimizers for Deep Learning","created":"2019-10-11","cited_by_count":103},{"id":"2012.04728","title":"Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics","created":"2020-12-08","cited_by_count":96},{"id":"2102.12470","title":"On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)","created":"2021-02-24","cited_by_count":73},{"id":"1812.03981","title":"Theoretical Analysis of Auto Rate-Tuning by Batch Normalization","created":"2018-12-10","cited_by_count":65},{"id":"1803.01814","title":"Norm matters: efficient and accurate normalization schemes in deep networks","created":"2018-03-05","cited_by_count":62},{"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":"1901.08168","title":"Loss Landscapes of Regularized Linear Autoencoders","created":"2019-01-23","cited_by_count":46},{"id":"1709.09603","title":"Riemannian approach to batch normalization","created":"2017-09-27","cited_by_count":35},{"id":"1906.04285","title":"Continuous Time Analysis of Momentum Methods","created":"2019-06-10","cited_by_count":32},{"id":"1303.0818","title":"Riemannian metrics for neural networks I: feedforward networks","created":"2013-03-04","cited_by_count":30},{"id":"2002.10376","title":"The Two Regimes of Deep Network Training","created":"2020-02-24","cited_by_count":30},{"id":"1611.02635","title":"A Lyapunov Analysis of Momentum Methods in Optimization","created":"2016-11-08","cited_by_count":28},{"id":"2102.06356","title":"A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes","created":"2021-02-12","cited_by_count":20},{"id":"1511.01029","title":"Understanding symmetries in deep networks","created":"2015-11-03","cited_by_count":17},{"id":"1803.01273","title":"Accelerating Natural Gradient with Higher-Order Invariance","created":"2018-03-04","cited_by_count":17},{"id":"2103.12682","title":"How to decay your learning rate","created":"2021-03-23","cited_by_count":11},{"id":"1803.03234","title":"Improving Optimization for Models With Continuous Symmetry Breaking","created":"2018-03-08","cited_by_count":8},{"id":"1808.10340","title":"A Coordinate-Free Construction of Scalable Natural Gradient","created":"2018-08-30","cited_by_count":6},{"id":"2006.08419","title":"Spherical Motion Dynamics: Learning Dynamics of Neural Network with Normalization, Weight Decay, and SGD","created":"2020-06-15","cited_by_count":6},{"id":"1509.03616","title":"On Accelerated Methods in Optimization","created":"2015-09-11","cited_by_count":5}],"next_cursor":null}