{"list":"other","total":73,"rows":[{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"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":"1408.5882","title":"Convolutional Neural Networks for Sentence Classification","created":"2014-08-25","cited_by_count":1127},{"id":"1607.01759","title":"Bag of Tricks for Efficient Text Classification","created":"2016-07-06","cited_by_count":876},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"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":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"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":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"1612.03651","title":"FastText.zip: Compressing text classification models","created":"2016-12-12","cited_by_count":335},{"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":"1705.07809","title":"Information-theoretic analysis of generalization capability of learning algorithms","created":"2017-05-22","cited_by_count":303},{"id":"1503.00036","title":"Norm-Based Capacity Control in Neural Networks","created":"2015-02-27","cited_by_count":299},{"id":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","cited_by_count":273},{"id":"1705.07832","title":"Concrete Dropout","created":"2017-05-22","cited_by_count":227},{"id":"1705.10941","title":"Spectral Norm Regularization for Improving the Generalizability of Deep Learning","created":"2017-05-31","cited_by_count":182},{"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":"1605.05101","title":"Recurrent Neural Network for Text Classification with Multi-Task Learning","created":"2016-05-17","cited_by_count":144},{"id":"1706.03662","title":"Practical Gauss-Newton Optimisation for Deep Learning","created":"2017-06-12","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":"1611.01353","title":"Information Dropout: Learning Optimal Representations Through Noisy Computation","created":"2016-11-04","cited_by_count":132},{"id":"1712.07628","title":"Improving Generalization Performance by Switching from Adam to SGD","created":"2017-12-20","cited_by_count":125},{"id":"1511.06422","title":"All you need is a good init","created":"2015-11-19","cited_by_count":124},{"id":"1506.04091","title":"On the properties of variational approximations of Gibbs posteriors","created":"2015-06-12","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":"1911.02151","title":"Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates","created":"2019-11-06","cited_by_count":119},{"id":"2007.12911","title":"Tighter risk certificates for neural networks","created":"2020-07-25","cited_by_count":112},{"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":"2002.11328","title":"Rethinking Bias-Variance Trade-off for Generalization of Neural Networks","created":"2020-02-26","cited_by_count":107},{"id":"1411.2664","title":"Preserving Statistical Validity in Adaptive Data Analysis","created":"2014-11-10","cited_by_count":103},{"id":"1711.01530","title":"Fisher-Rao Metric, Geometry, and Complexity of Neural Networks","created":"2017-11-05","cited_by_count":100},{"id":"1307.1493","title":"Dropout Training as Adaptive Regularization","created":"2013-07-04","cited_by_count":93},{"id":"2009.12836","title":"Normalization Techniques in Training DNNs: Methodology, Analysis and Application","created":"2020-09-27","cited_by_count":90},{"id":"2004.12983","title":"Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms","created":"2020-04-27","cited_by_count":89},{"id":"1807.05031","title":"On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length","created":"2018-07-13","cited_by_count":88},{"id":"1802.08241","title":"Hessian-based Analysis of Large Batch Training and Robustness to Adversaries","created":"2018-02-22","cited_by_count":87},{"id":"1506.02629","title":"Generalization in Adaptive Data Analysis and Holdout Reuse","created":"2015-06-08","cited_by_count":83},{"id":"1712.09376","title":"Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors","created":"2017-12-26","cited_by_count":81},{"id":"2010.11924","title":"In Search of Robust Measures of Generalization","created":"2020-10-22","cited_by_count":79},{"id":"1802.08770","title":"A Walk with SGD","created":"2018-02-24","cited_by_count":78},{"id":"2002.12915","title":"The Implicit and Explicit Regularization Effects of Dropout","created":"2020-02-28","cited_by_count":71},{"id":"1811.07457","title":"Generalizable Adversarial Training via Spectral Normalization","created":"2018-11-19","cited_by_count":68},{"id":"2006.13057","title":"PAC-Bayes Analysis Beyond the Usual Bounds","created":"2020-06-23","cited_by_count":63},{"id":"1608.05610","title":"A Strongly Quasiconvex PAC-Bayesian Bound","created":"2016-08-19","cited_by_count":54},{"id":"1901.01672","title":"Generalization in Deep Networks: The Role of Distance from Initialization","created":"2019-01-07","cited_by_count":51},{"id":"2005.00695","title":"On the Generalization Effects of Linear Transformations in Data Augmentation","created":"2020-05-02","cited_by_count":47},{"id":"1307.2118","title":"A PAC-Bayesian Tutorial with A Dropout Bound","created":"2013-07-08","cited_by_count":43},{"id":"2006.07279","title":"PAC-Bayes unleashed: generalisation bounds with unbounded losses","created":"2020-06-12","cited_by_count":43},{"id":"2012.07976","title":"NeurIPS 2020 Competition: Predicting Generalization in Deep Learning","created":"2020-12-14","cited_by_count":41},{"id":"1912.00528","title":"The intriguing role of module criticality in the generalization of deep networks","created":"2019-12-02","cited_by_count":40},{"id":"1905.10259","title":"Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks","created":"2019-05-24","cited_by_count":38},{"id":"2002.07933","title":"Improving Generalization by Controlling Label-Noise Information in Neural Network Weights","created":"2020-02-19","cited_by_count":35},{"id":"2101.01761","title":"AutoDropout: Learning Dropout Patterns to Regularize Deep Networks","created":"2021-01-05","cited_by_count":35},{"id":"2010.05983","title":"How does Weight Correlation Affect the Generalisation Ability of Deep Neural Networks","created":"2020-10-12","cited_by_count":32},{"id":"2004.11627","title":"Convolution-Weight-Distribution Assumption: Rethinking the Criteria of Channel Pruning","created":"2020-04-24","cited_by_count":30},{"id":"2012.02775","title":"Representation Based Complexity Measures for Predicting Generalization in Deep Learning","created":"2020-12-04","cited_by_count":29},{"id":"2103.04181","title":"Contextual Dropout: An Efficient Sample-Dependent Dropout Module","created":"2021-03-06","cited_by_count":26},{"id":"1806.09777","title":"On the Implicit Bias of Dropout","created":"2018-06-26","cited_by_count":22},{"id":"2109.10304","title":"Learning PAC-Bayes Priors for Probabilistic Neural Networks","created":"2021-09-21","cited_by_count":21},{"id":"1412.4736","title":"On the Inductive Bias of Dropout","created":"2014-12-15","cited_by_count":19},{"id":"2010.12711","title":"On Convergence and Generalization of Dropout Training","created":"2020-10-23","cited_by_count":19},{"id":"1710.05092","title":"Dropout as a Low-Rank Regularizer for Matrix Factorization","created":"2017-10-13","cited_by_count":14},{"id":"1905.11887","title":"On Dropout and Nuclear Norm Regularization","created":"2019-05-28","cited_by_count":12},{"id":"2011.12737","title":"Ranking Deep Learning Generalization using Label Variation in Latent Geometry Graphs","created":"2020-11-25","cited_by_count":6}],"next_cursor":null}