{"list":"other","total":59,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"1502.02791","title":"Learning Transferable Features with Deep Adaptation Networks","created":"2015-02-10","cited_by_count":1329},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"1506.01186","title":"Cyclical Learning Rates for Training Neural Networks","created":"2015-06-03","cited_by_count":629},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"1906.11300","title":"Benign Overfitting in Linear Regression","created":"2019-06-26","cited_by_count":549},{"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":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"id":"1905.03696","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","created":"2019-04-29","cited_by_count":402},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"1907.08610","title":"Lookahead Optimizer: k steps forward, 1 step back","created":"2019-07-19","cited_by_count":336},{"id":"1711.00489","title":"Don't Decay the Learning Rate, Increase the Batch Size","created":"2017-11-01","cited_by_count":320},{"id":"1707.09564","title":"A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks","created":"2017-07-29","cited_by_count":314},{"id":"1912.07145","title":"PyHessian: Neural Networks Through the Lens of the Hessian","created":"2019-12-16","cited_by_count":292},{"id":"2010.07468","title":"AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients","created":"2020-10-15","cited_by_count":283},{"id":"1705.08292","title":"The Marginal Value of Adaptive Gradient Methods in Machine Learning","created":"2017-05-23","cited_by_count":250},{"id":"2003.02218","title":"The large learning rate phase of deep learning: the catapult mechanism","created":"2020-03-04","cited_by_count":216},{"id":"1810.01075","title":"Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning","created":"2018-10-02","cited_by_count":215},{"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":"2006.00719","title":"ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning","created":"2020-06-01","cited_by_count":202},{"id":"1705.10941","title":"Spectral Norm Regularization for Improving the Generalizability of Deep Learning","created":"2017-05-31","cited_by_count":182},{"id":"2102.11535","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","created":"2021-02-23","cited_by_count":169},{"id":"1710.06451","title":"A Bayesian Perspective on Generalization and Stochastic Gradient Descent","created":"2017-10-17","cited_by_count":135},{"id":"2006.04740","title":"The Heavy-Tail Phenomenon in SGD","created":"2020-06-08","cited_by_count":124},{"id":"1708.03395","title":"Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Models","created":"2017-08-10","cited_by_count":116},{"id":"2002.06716","title":"Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data","created":"2020-02-17","cited_by_count":115},{"id":"1901.08276","title":"Traditional and Heavy-Tailed Self Regularization in Neural Network Models","created":"2019-01-24","cited_by_count":105},{"id":"1806.01316","title":"Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach","created":"2018-06-04","cited_by_count":91},{"id":"1906.09777","title":"A Tensorized Transformer for Language Modeling","created":"2019-06-24","cited_by_count":86},{"id":"2010.11924","title":"In Search of Robust Measures of Generalization","created":"2020-10-22","cited_by_count":79},{"id":"1909.11304","title":"Asymptotics of Wide Networks from Feynman Diagrams","created":"2019-09-25","cited_by_count":77},{"id":"2006.09313","title":"Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks","created":"2020-06-16","cited_by_count":62},{"id":"2210.01787","title":"Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective","created":"2022-10-04","cited_by_count":51},{"id":"1901.08278","title":"Heavy-Tailed Universality Predicts Trends in Test Accuracies for Very Large Pre-Trained Deep Neural Networks","created":"2019-01-24","cited_by_count":44},{"id":"1803.06969","title":"Comparing Dynamics: Deep Neural Networks versus Glassy Systems","created":"2018-03-19","cited_by_count":42},{"id":"1906.04659","title":"Stable Rank Normalization for Improved Generalization in Neural Networks and GANs","created":"2019-06-11","cited_by_count":41},{"id":"2107.11228","title":"Taxonomizing local versus global structure in neural network loss landscapes","created":"2021-07-23","cited_by_count":34},{"id":"1910.05992","title":"Pathological spectra of the Fisher information metric and its variants in deep neural networks","created":"2019-10-14","cited_by_count":32},{"id":"2108.00781","title":"Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers","created":"2021-08-02","cited_by_count":27},{"id":"1710.09553","title":"Rethinking generalization requires revisiting old ideas: statistical mechanics approaches and complex learning behavior","created":"2017-10-26","cited_by_count":25},{"id":"1510.04609","title":"Layer-Specific Adaptive Learning Rates for Deep Networks","created":"2015-10-15","cited_by_count":19},{"id":"2106.00734","title":"Post-mortem on a deep learning contest: a Simpson's paradox and the complementary roles of scale metrics versus shape metrics","created":"2021-06-01","cited_by_count":19},{"id":"2012.04729","title":"On 1/n neural representation and robustness","created":"2020-12-08","cited_by_count":17},{"id":"2201.13011","title":"On the Power-Law Hessian Spectrums in Deep Learning","created":"2022-01-31","cited_by_count":16},{"id":"2301.11885","title":"Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions","created":"2023-01-27","cited_by_count":15},{"id":"2305.18383","title":"A Three-regime Model of Network Pruning","created":"2023-05-28","cited_by_count":15},{"id":"2111.11986","title":"HERO: Hessian-Enhanced Robust Optimization for Unifying and Improving Generalization and Quantization Performance","created":"2021-11-23","cited_by_count":8},{"id":"2304.02911","title":"Heavy-Tailed Regularization of Weight Matrices in Deep Neural Networks","created":"2023-04-06","cited_by_count":7}],"next_cursor":null}