{"list":"other","total":74,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"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":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"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":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1901.08584","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","created":"2019-01-24","cited_by_count":566},{"id":"1708.03888","title":"Large Batch Training of Convolutional Networks","created":"2017-08-13","cited_by_count":535},{"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":"1812.01187","title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","created":"2018-12-04","cited_by_count":431},{"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":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"1905.11881","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","created":"2019-05-28","cited_by_count":341},{"id":"1802.06509","title":"On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization","created":"2018-02-19","cited_by_count":284},{"id":"1812.06162","title":"An Empirical Model of Large-Batch Training","created":"2018-12-14","cited_by_count":281},{"id":"1705.08741","title":"Train longer, generalize better: closing the generalization gap in large batch training of neural networks","created":"2017-05-24","cited_by_count":279},{"id":"1410.0759","title":"cuDNN: Efficient Primitives for Deep Learning","created":"2014-10-03","cited_by_count":245},{"id":"1503.02101","title":"Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition","created":"2015-03-06","cited_by_count":243},{"id":"1710.03667","title":"High-dimensional dynamics of generalization error in neural networks","created":"2017-10-10","cited_by_count":241},{"id":"2003.02218","title":"The large learning rate phase of deep learning: the catapult mechanism","created":"2020-03-04","cited_by_count":216},{"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":"1811.03600","title":"Measuring the Effects of Data Parallelism on Neural Network Training","created":"2018-11-08","cited_by_count":193},{"id":"2101.12176","title":"On the Origin of Implicit Regularization in Stochastic Gradient Descent","created":"2021-01-28","cited_by_count":184},{"id":"2006.06914","title":"Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses","created":"2020-06-12","cited_by_count":173},{"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":"1712.06559","title":"The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning","created":"2017-12-18","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":"1805.12076","title":"Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks","created":"2018-05-30","cited_by_count":142},{"id":"1710.06451","title":"A Bayesian Perspective on Generalization and Stochastic Gradient Descent","created":"2017-10-17","cited_by_count":135},{"id":"2010.05627","title":"Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning","created":"2020-10-12","cited_by_count":126},{"id":"1910.07454","title":"An Exponential Learning Rate Schedule for Deep Learning","created":"2019-10-16","cited_by_count":121},{"id":"2007.01547","title":"Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers","created":"2020-07-03","cited_by_count":119},{"id":"1907.04164","title":"Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model","created":"2019-07-09","cited_by_count":117},{"id":"1710.11029","title":"Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks","created":"2017-10-30","cited_by_count":109},{"id":"2005.10785","title":"Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping","created":"2020-05-21","cited_by_count":104},{"id":"1804.07612","title":"Revisiting Small Batch Training for Deep Neural Networks","created":"2018-04-20","cited_by_count":102},{"id":"2010.02519","title":"Improved Analysis of Clipping Algorithms for Non-convex Optimization","created":"2020-10-05","cited_by_count":89},{"id":"2006.08680","title":"Shape Matters: Understanding the Implicit Bias of the Noise Covariance","created":"2020-06-15","cited_by_count":88},{"id":"1706.10239","title":"Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes","created":"2017-06-30","cited_by_count":84},{"id":"2006.15081","title":"On the Generalization Benefit of Noise in Stochastic Gradient Descent","created":"2020-06-26","cited_by_count":82},{"id":"1802.08770","title":"A Walk with SGD","created":"2018-02-24","cited_by_count":78},{"id":"1705.10412","title":"Gradient Descent Can Take Exponential Time to Escape Saddle Points","created":"2017-05-29","cited_by_count":74},{"id":"2102.12470","title":"On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)","created":"2021-02-24","cited_by_count":73},{"id":"1807.11205","title":"Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes","created":"2018-07-30","cited_by_count":63},{"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":"1906.03291","title":"Understanding Generalization through Visualizations","created":"2019-06-07","cited_by_count":54},{"id":"2002.10657","title":"Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based Optimization","created":"2020-02-25","cited_by_count":41},{"id":"2102.01117","title":"SGD Generalizes Better Than GD (And Regularization Doesn't Help)","created":"2021-02-01","cited_by_count":38},{"id":"1811.12019","title":"Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networks","created":"2018-11-29","cited_by_count":37},{"id":"2106.13897","title":"Implicit Gradient Alignment in Distributed and Federated Learning","created":"2021-06-25","cited_by_count":29},{"id":"2010.14495","title":"Are wider nets better given the same number of parameters?","created":"2020-10-27","cited_by_count":27},{"id":"2002.06189","title":"Stochasticity of Deterministic Gradient Descent: Large Learning Rate for Multiscale Objective Function","created":"2020-02-14","cited_by_count":26},{"id":"1811.12941","title":"On the Computational Inefficiency of Large Batch Sizes for Stochastic Gradient Descent","created":"2018-11-30","cited_by_count":25},{"id":"1901.08256","title":"Large-Batch Training for LSTM and Beyond","created":"2019-01-24","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":"2008.13363","title":"Extreme Memorization via Scale of Initialization","created":"2020-08-31","cited_by_count":18},{"id":"1909.12340","title":"At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks?","created":"2019-09-26","cited_by_count":16},{"id":"2003.06152","title":"Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study","created":"2020-03-13","cited_by_count":16},{"id":"2107.00469","title":"Never Go Full Batch (in Stochastic Convex Optimization)","created":"2021-06-29","cited_by_count":14},{"id":"1903.12650","title":"Yet Another Accelerated SGD: ResNet-50 Training on ImageNet in 74.7 seconds","created":"2019-03-29","cited_by_count":12},{"id":"2104.04874","title":"SGD Implicitly Regularizes Generalization Error","created":"2021-04-10","cited_by_count":10},{"id":"1812.00542","title":"Towards Theoretical Understanding of Large Batch Training in Stochastic Gradient Descent","created":"2018-12-03","cited_by_count":6},{"id":"2006.08517","title":"The Limit of the Batch Size","created":"2020-06-15","cited_by_count":6}],"next_cursor":null}