{"list":"other","total":53,"rows":[{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1901.08573","title":"Theoretically Principled Trade-off between Robustness and Accuracy","created":"2019-01-24","cited_by_count":1517},{"id":"1902.02918","title":"Certified Adversarial Robustness via Randomized Smoothing","created":"2019-02-08","cited_by_count":1340},{"id":"1805.12152","title":"Robustness May Be at Odds with Accuracy","created":"2018-05-30","cited_by_count":880},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"id":"1511.06464","title":"Unitary Evolution Recurrent Neural Networks","created":"2015-11-20","cited_by_count":294},{"id":"1704.08847","title":"Parseval Networks: Improving Robustness to Adversarial Examples","created":"2017-04-28","cited_by_count":293},{"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":"1811.05381","title":"Sorting out Lipschitz function approximation","created":"2018-11-13","cited_by_count":213},{"id":"1802.04034","title":"Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks","created":"2018-02-12","cited_by_count":195},{"id":"1711.00436","title":"Hierarchical Representations for Efficient Architecture Search","created":"2017-11-01","cited_by_count":191},{"id":"1705.08475","title":"Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation","created":"2017-05-23","cited_by_count":185},{"id":"1806.05393","title":"Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks","created":"2018-06-14","cited_by_count":176},{"id":"2106.10165","title":"The Principles of Deep Learning Theory","created":"2021-06-18","cited_by_count":173},{"id":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154},{"id":"1901.08428","title":"Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group","created":"2019-01-24","cited_by_count":134},{"id":"1711.04735","title":"Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice","created":"2017-11-13","cited_by_count":132},{"id":"2102.08452","title":"Globally-Robust Neural Networks","created":"2021-02-16","cited_by_count":108},{"id":"2104.07167","title":"Orthogonalizing Convolutional Layers with the Cayley Transform","created":"2021-04-14","cited_by_count":105},{"id":"1903.12561","title":"Adversarial Robustness vs Model Compression, or Both?","created":"2019-03-29","cited_by_count":98},{"id":"1911.00937","title":"Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks","created":"2019-11-03","cited_by_count":87},{"id":"2002.01113","title":"Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform","created":"2020-02-04","cited_by_count":80},{"id":"1902.03538","title":"Model Compression with Adversarial Robustness: A Unified Optimization Framework","created":"2019-02-10","cited_by_count":71},{"id":"1810.01279","title":"Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network","created":"2018-10-01","cited_by_count":69},{"id":"2105.11417","title":"Skew Orthogonal Convolutions","created":"2021-05-24","cited_by_count":67},{"id":"1910.05505","title":"Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers","created":"2019-10-12","cited_by_count":61},{"id":"2103.03936","title":"Pufferfish: Communication-efficient Models At No Extra Cost","created":"2021-03-05","cited_by_count":61},{"id":"2110.12690","title":"A Dynamical System Perspective for Lipschitz Neural Networks","created":"2021-10-25","cited_by_count":60},{"id":"1905.12600","title":"Generalization bounds for deep convolutional neural networks","created":"2019-05-29","cited_by_count":59},{"id":"2105.01029","title":"Initialization and Regularization of Factorized Neural Layers","created":"2021-05-03","cited_by_count":58},{"id":"2004.09031","title":"Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification","created":"2020-04-20","cited_by_count":53},{"id":"2106.16225","title":"Analytic Insights into Structure and Rank of Neural Network Hessian Maps","created":"2021-06-30","cited_by_count":52},{"id":"2108.04062","title":"Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100","created":"2021-08-05","cited_by_count":47},{"id":"2206.06072","title":"Rank Diminishing in Deep Neural Networks","created":"2022-06-13","cited_by_count":47},{"id":"2205.13571","title":"Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations","created":"2022-05-26","cited_by_count":43},{"id":"2102.07432","title":"Fast and accurate optimization on the orthogonal manifold without retraction","created":"2021-02-15","cited_by_count":35},{"id":"1709.06030","title":"N2N Learning: Network to Network Compression via Policy Gradient Reinforcement Learning","created":"2017-09-18","cited_by_count":33},{"id":"1907.05681","title":"Adversarial Lipschitz Regularization","created":"2019-07-12","cited_by_count":30},{"id":"1611.06013","title":"Improving training of deep neural networks via Singular Value Bounding","created":"2016-11-18","cited_by_count":26},{"id":"2109.02235","title":"Gradient Normalization for Generative Adversarial Networks","created":"2021-09-06","cited_by_count":25},{"id":"2108.04890","title":"On the Effect of Pruning on Adversarial Robustness","created":"2021-08-10","cited_by_count":23},{"id":"1705.03387","title":"Generative Adversarial Trainer: Defense to Adversarial Perturbations with GAN","created":"2017-05-09","cited_by_count":20},{"id":"2009.05423","title":"Achieving Adversarial Robustness via Sparsity","created":"2020-09-11","cited_by_count":14},{"id":"2108.06885","title":"Neural Architecture Dilation for Adversarial Robustness","created":"2021-08-16","cited_by_count":13},{"id":"1811.04142","title":"Complex Unitary Recurrent Neural Networks using Scaled Cayley Transform","created":"2018-11-09","cited_by_count":12},{"id":"1901.10371","title":"On the Effect of Low-Rank Weights on Adversarial Robustness of Neural Networks","created":"2019-01-29","cited_by_count":7}],"next_cursor":null}