{"list":"other","total":71,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1901.08573","title":"Theoretically Principled Trade-off between Robustness and Accuracy","created":"2019-01-24","cited_by_count":1517},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"2003.01690","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","created":"2020-03-03","cited_by_count":1451},{"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":"1705.07204","title":"Ensemble Adversarial Training: Attacks and Defenses","created":"2017-05-19","cited_by_count":840},{"id":"1412.1897","title":"Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images","created":"2014-12-05","cited_by_count":776},{"id":"1606.07792","title":"Wide & Deep Learning for Recommender Systems","created":"2016-06-24","cited_by_count":747},{"id":"2001.03994","title":"Fast is better than free: Revisiting adversarial training","created":"2020-01-12","cited_by_count":727},{"id":"1904.12843","title":"Adversarial Training for Free!","created":"2019-04-29","cited_by_count":643},{"id":"2002.11569","title":"Overfitting in adversarially robust deep learning","created":"2020-02-26","cited_by_count":506},{"id":"1905.13736","title":"Unlabeled Data Improves Adversarial Robustness","created":"2019-05-31","cited_by_count":416},{"id":"1805.07984","title":"Adversarial Attacks on Neural Networks for Graph Data","created":"2018-05-21","cited_by_count":397},{"id":"1901.09960","title":"Using Pre-Training Can Improve Model Robustness and Uncertainty","created":"2019-01-28","cited_by_count":373},{"id":"1711.00489","title":"Don't Decay the Learning Rate, Increase the Batch Size","created":"2017-11-01","cited_by_count":320},{"id":"1804.11285","title":"Adversarially Robust Generalization Requires More Data","created":"2018-04-30","cited_by_count":318},{"id":"1704.04289","title":"Stochastic Gradient Descent as Approximate Bayesian Inference","created":"2017-04-13","cited_by_count":300},{"id":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","cited_by_count":273},{"id":"1906.00331","title":"On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems","created":"2019-06-02","cited_by_count":270},{"id":"1810.00069","title":"Adversarial Attacks and Defences: A Survey","created":"2018-09-28","cited_by_count":259},{"id":"2010.00467","title":"Bag of Tricks for Adversarial Training","created":"2020-10-01","cited_by_count":200},{"id":"1905.00877","title":"You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle","created":"2019-05-02","cited_by_count":183},{"id":"1812.02637","title":"MMA Training: Direct Input Space Margin Maximization through Adversarial Training","created":"2018-12-06","cited_by_count":172},{"id":"1905.13725","title":"Are Labels Required for Improving Adversarial Robustness?","created":"2019-05-31","cited_by_count":163},{"id":"1907.02610","title":"Adversarial Robustness through Local Linearization","created":"2019-07-04","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":"1710.06451","title":"A Bayesian Perspective on Generalization and Stochastic Gradient Descent","created":"2017-10-17","cited_by_count":135},{"id":"1901.05353","title":"A Primer on PAC-Bayesian Learning","created":"2019-01-16","cited_by_count":132},{"id":"2112.08304","title":"On the Convergence and Robustness of Adversarial Training","created":"2021-12-15","cited_by_count":130},{"id":"2002.02417","title":"Near-Optimal Algorithms for Minimax Optimization","created":"2020-02-05","cited_by_count":119},{"id":"1804.00097","title":"Adversarial Attacks and Defences Competition","created":"2018-03-31","cited_by_count":96},{"id":"2006.12792","title":"RayS: A Ray Searching Method for Hard-label Adversarial Attack","created":"2020-06-23","cited_by_count":96},{"id":"1907.10764","title":"Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training","created":"2019-07-24","cited_by_count":95},{"id":"1805.04807","title":"Curriculum Adversarial Training","created":"2018-05-13","cited_by_count":89},{"id":"1811.11304","title":"Universal Adversarial Training","created":"2018-11-27","cited_by_count":87},{"id":"1909.00900","title":"Metric Learning for Adversarial Robustness","created":"2019-09-03","cited_by_count":77},{"id":"1905.11911","title":"Controlling Neural Level Sets","created":"2019-05-28","cited_by_count":76},{"id":"2112.12376","title":"Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization","created":"2021-12-23","cited_by_count":76},{"id":"1803.05999","title":"Escaping Saddles with Stochastic Gradients","created":"2018-03-15","cited_by_count":66},{"id":"2102.11165","title":"Few-shot Network Anomaly Detection via Cross-network Meta-learning","created":"2021-02-22","cited_by_count":64},{"id":"1901.08572","title":"Width Provably Matters in Optimization for Deep Linear Neural Networks","created":"2019-01-24","cited_by_count":52},{"id":"1910.13962","title":"Understanding the Role of Momentum in Stochastic Gradient Methods","created":"2019-10-30","cited_by_count":44},{"id":"2012.03636","title":"Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent","created":"2020-12-07","cited_by_count":37},{"id":"1709.06617","title":"A PAC-Bayesian Analysis of Randomized Learning with Application to Stochastic Gradient Descent","created":"2017-09-19","cited_by_count":29},{"id":"2103.17182","title":"Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization","created":"2021-03-31","cited_by_count":28},{"id":"1704.04932","title":"Deep Relaxation: partial differential equations for optimizing deep neural networks","created":"2017-04-17","cited_by_count":27},{"id":"2211.16080","title":"Understanding and Enhancing Robustness of Concept-based Models","created":"2022-11-29","cited_by_count":22},{"id":"2212.04983","title":"Adversarial Weight Perturbation Improves Generalization in Graph Neural Networks","created":"2022-12-09","cited_by_count":21},{"id":"1905.09591","title":"A Direct Approach to Robust Deep Learning Using Adversarial Networks","created":"2019-05-23","cited_by_count":18},{"id":"2206.04789","title":"Comprehensive Fair Meta-learned Recommender System","created":"2022-06-09","cited_by_count":18},{"id":"2206.11225","title":"RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval","created":"2022-06-17","cited_by_count":15},{"id":"1803.00195","title":"The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects","created":"2018-03-01","cited_by_count":9},{"id":"1808.01976","title":"Adversarial Vision Challenge","created":"2018-08-06","cited_by_count":9},{"id":"2302.03825","title":"Decentralized Riemannian Algorithm for Nonconvex Minimax Problems","created":"2023-02-08","cited_by_count":7},{"id":"2006.00387","title":"Exploring Model Robustness with Adaptive Networks and Improved Adversarial Training","created":"2020-05-30","cited_by_count":2}],"next_cursor":null}