{"list":"other","total":51,"rows":[{"id":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"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":"1902.02918","title":"Certified Adversarial Robustness via Randomized Smoothing","created":"2019-02-08","cited_by_count":1340},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"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":"1402.1869","title":"On the Number of Linear Regions of Deep Neural Networks","created":"2014-02-08","cited_by_count":381},{"id":"1906.04584","title":"Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers","created":"2019-06-09","cited_by_count":330},{"id":"2104.08894","title":"The Intrinsic Dimension of Images and Its Impact on Learning","created":"2021-04-18","cited_by_count":315},{"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":"1804.04368","title":"Regularisation of Neural Networks by Enforcing Lipschitz Continuity","created":"2018-04-12","cited_by_count":314},{"id":"1703.02930","title":"Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks","created":"2017-03-08","cited_by_count":311},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"1503.00036","title":"Norm-Based Capacity Control in Neural Networks","created":"2015-02-27","cited_by_count":299},{"id":"1704.08847","title":"Parseval Networks: Improving Robustness to Adversarial Examples","created":"2017-04-28","cited_by_count":293},{"id":"1906.04893","title":"Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks","created":"2019-06-12","cited_by_count":293},{"id":"1505.05116","title":"Data-driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulations","created":"2015-05-19","cited_by_count":291},{"id":"1712.06541","title":"Size-Independent Sample Complexity of Neural Networks","created":"2017-12-18","cited_by_count":290},{"id":"1806.00468","title":"Implicit Bias of Gradient Descent on Linear Convolutional Networks","created":"2018-06-01","cited_by_count":251},{"id":"1811.05381","title":"Sorting out Lipschitz function approximation","created":"2018-11-13","cited_by_count":213},{"id":"1604.02199","title":"Distributionally Robust Stochastic Optimization with Wasserstein Distance","created":"2016-04-08","cited_by_count":185},{"id":"1908.08729","title":"Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning","created":"2019-08-23","cited_by_count":170},{"id":"1903.11680","title":"Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks","created":"2019-03-27","cited_by_count":159},{"id":"2009.08295","title":"Neural Rough Differential Equations for Long Time Series","created":"2020-09-17","cited_by_count":143},{"id":"1804.05862","title":"Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach","created":"2018-04-16","cited_by_count":126},{"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":"1605.08254","title":"Robust Large Margin Deep Neural Networks","created":"2016-05-26","cited_by_count":118},{"id":"1810.00113","title":"Predicting the Generalization Gap in Deep Networks with Margin Distributions","created":"2018-09-28","cited_by_count":113},{"id":"2003.01219","title":"Exactly Computing the Local Lipschitz Constant of ReLU Networks","created":"2020-03-02","cited_by_count":102},{"id":"1906.09477","title":"The phase diagram of approximation rates for deep neural networks","created":"2019-06-22","cited_by_count":88},{"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":"2104.08938","title":"On the approximation of functions by tanh neural networks","created":"2021-04-18","cited_by_count":81},{"id":"1905.10943","title":"Distributionally Robust Optimization and Generalization in Kernel Methods","created":"2019-05-27","cited_by_count":73},{"id":"2009.04382","title":"Finite-Sample Guarantees for Wasserstein Distributionally Robust Optimization: Breaking the Curse of Dimensionality","created":"2020-09-09","cited_by_count":49},{"id":"1610.07193","title":"Simpler PAC-Bayesian Bounds for Hostile Data","created":"2016-10-23","cited_by_count":46},{"id":"1911.02088","title":"An Alternative Probabilistic Interpretation of the Huber Loss","created":"2019-11-05","cited_by_count":43},{"id":"1905.13367","title":"PAC-Bayes Un-Expected Bernstein Inequality","created":"2019-05-31","cited_by_count":36},{"id":"2005.02505","title":"A generative adversarial network approach to calibration of local stochastic volatility models","created":"2020-05-05","cited_by_count":29},{"id":"2010.08479","title":"Failures of model-dependent generalization bounds for least-norm interpolation","created":"2020-10-16","cited_by_count":26},{"id":"1910.10783","title":"Wasserstein Smoothing: Certified Robustness against Wasserstein Adversarial Attacks","created":"2019-10-23","cited_by_count":25},{"id":"2008.06631","title":"On the Generalization Properties of Adversarial Training","created":"2020-08-15","cited_by_count":23},{"id":"2002.04197","title":"Generalised Lipschitz Regularisation Equals Distributional Robustness","created":"2020-02-11","cited_by_count":14},{"id":"2202.13216","title":"Adversarial robustness of sparse local Lipschitz predictors","created":"2022-02-26","cited_by_count":11},{"id":"2103.06002","title":"Robustness to Pruning Predicts Generalization in Deep Neural Networks","created":"2021-03-10","cited_by_count":10},{"id":"2202.05568","title":"Change of measure through the Legendre transform","created":"2022-02-11","cited_by_count":10},{"id":"1809.00082","title":"NEU: A Meta-Algorithm for Universal UAP-Invariant Feature Representation","created":"2018-08-31","cited_by_count":6}],"next_cursor":null}